© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31228
    Prev
    Next
    INDEX
    Explanations

    needs

    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
    Negative Logits
    illet
    -0.07
    гин
    -0.07
    whether
    -0.07
     proph
    -0.07
    游戏里的
    -0.06
    葳
    -0.06
     biom
    -0.06
     wipes
    -0.06
    电
    -0.06
     Reggie
    -0.06
    POSITIVE LOGITS
    CB
    0.08
     defaults
    0.07
    出色
    0.07
     incur
    0.07
    IndexOf
    0.07
     OECD
    0.07
    颗粒
    0.07
    amples
    0.07
     corresponds
    0.06
     Universe
    0.06
    Activations Density 0.012%

    No Known Activations