© 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 EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 71185
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indigenous
    -0.06
    ตก
    -0.06
    Jac
    -0.06
    ,max
    -0.06
     jos
    -0.06
     Historic
    -0.06
     meaningful
    -0.06
     county
    -0.06
     plateau
    -0.06
     king
    -0.06
    POSITIVE LOGITS
    党员
    0.07
    📅
    0.07
    jay
    0.07
    サラ
    0.07
    禔
    0.07
    /editor
    0.07
    bones
    0.06
    疐
    0.06
    WebHost
    0.06
    _COMMIT
    0.06
    Activations Density 0.104%

    No Known Activations