© 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. 70643
    Prev
    Next
    INDEX
    Explanations

    interview excerpts

    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
    ランス
    -0.08
     domaine
    -0.07
    liśmy
    -0.07
    ］
    -0.07
    ней
    -0.07
     interes
    -0.07
    アジア
    -0.07
    Britain
    -0.07
    נו
    -0.07
     económ
    -0.06
    POSITIVE LOGITS
    大发
    0.08
     selectively
    0.07
    奢
    0.07
    不得已
    0.07
     Vu
    0.07
     Vietnamese
    0.07
    Except
    0.07
     adventures
    0.07
    Event
    0.07
    workers
    0.07
    Activations Density 0.062%

    No Known Activations