© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 117493
    Prev
    Next
    INDEX
    Explanations

    Second person

    np_max-act · gemini-2.0-flash

    references to the speaker or listener—especially first- and second-person pronouns and their possessive forms—signaling self-reference or direct address.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    first- and second-person pronouns and possessives indicating self-reference or direct address.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    本轮
    -0.07
    蜒
    -0.06
    Tweet
    -0.06
    rawl
    -0.06
    )Math
    -0.06
    izarre
    -0.06
    .update
    -0.06
    \Collection
    -0.06
     Neuroscience
    -0.06
     Feed
    -0.06
    POSITIVE LOGITS
     prepared
    0.08
     doit
    0.08
    ach
    0.07
    竞争对手
    0.07
    ch
    0.07
    服务区
    0.07
    akah
    0.07
    uta
    0.07
     точки
    0.07
    hei
    0.07
    Activations Density 0.372%

    No Known Activations