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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2118
    Prev
    Next
    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash

    first-person present-progressive statements indicating the author is currently doing or attempting something.

    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
     Wonder
    -0.08
    Pattern
    -0.07
    Вы
    -0.07
     Madonna
    -0.07
     msg
    -0.07
     votes
    -0.07
     Draft
    -0.07
     robot
    -0.07
    🐣
    -0.07
    zung
    -0.07
    POSITIVE LOGITS
    Ｌ
    0.07
     zależy
    0.07
    牺
    0.06
     freezes
    0.06
    ╱
    0.06
    cel
    0.06
    indle
    0.06
    医护
    0.06
    POOL
    0.06
    极大地
    0.06
    Activations Density 0.034%

    No Known Activations