© 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. 7-RESID-POST-AA
    11. 11335
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    排除
    -0.08
     resist
    -0.07
    _stage
    -0.07
    getPage
    -0.07
     zz
    -0.07
     tipped
    -0.07
    𝗘
    -0.06
    Pel
    -0.06
    paged
    -0.06
    線上
    -0.06
    POSITIVE LOGITS
    到时候
    0.07
    作った
    0.07
    (return
    0.07
    通知书
    0.07
     העבודה
    0.07
    してる
    0.07
    运河
    0.07
     culinary
    0.07
     dönüş
    0.07
    ullet
    0.07
    Activations Density 0.002%

    No Known Activations