© 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. 122548
    Prev
    Next
    INDEX
    Explanations

    Webpage content

    np_max-act · gemini-2.0-flash

    chat-formatting boundaries, specifically the end of a user message block in role-tagged transcripts.

    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
    ивается
    -0.07
    »,
    -0.07
    iquer
    -0.07
    ulously
    -0.07
    成
    -0.07
    abile
    -0.06
    院院士
    -0.06
     sites
    -0.06
    oor
    -0.06
    يلي
    -0.06
    POSITIVE LOGITS
     Narr
    0.08
    nearest
    0.07
    etype
    0.07
    -fe
    0.07
     objetos
    0.07
    /Object
    0.06
     orm
    0.06
     RequestOptions
    0.06
     tet
    0.06
    뀨
    0.06
    Activations Density 0.073%

    No Known Activations