© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97322
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    caff
    -0.25
    ols
    -0.25
     realidad
    -0.25
     disp
    -0.24
    oons
    -0.23
     encaps
    -0.23
    æ¬ł
    -0.23
    -mf
    -0.23
     clearly
    -0.23
    ail
    -0.23
    POSITIVE LOGITS
     khám
    0.28
    è¿IJèIJ¥åķĨ
    0.28
    个交æĺĵ
    0.27
    éªĸ
    0.26
    亲
    0.26
    dfd
    0.26
    æĽ´å¼º
    0.25
    çķ¸
    0.25
    ActionCreators
    0.25
    лег
    0.25
    Activations Density 0.026%

    No Known Activations