© 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. 50252
    Prev
    Next
    INDEX
    Explanations

    code/data/formulas

    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
    éro
    -0.07
     Significant
    -0.07
     boca
    -0.07
    这样做
    -0.06
    ORDER
    -0.06
    key
    -0.06
     predecessors
    -0.06
     redesigned
    -0.06
    ממוצע
    -0.06
    Apparently
    -0.06
    POSITIVE LOGITS
     wages
    0.07
     indu
    0.07
     corrosion
    0.07
    鳎
    0.07
    movie
    0.06
     dreadful
    0.06
     taxation
    0.06
     mee
    0.06
    有一些
    0.06
    yield
    0.06
    Activations Density 21.223%

    No Known Activations