© 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. 32-TRANSCODER-HP
    7. 41008
    Prev
    Next
    INDEX
    Explanations

    code and software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ³ķ
    -1.28
    -fr
    -1.05
    æ³ķåĽ½
    -1.03
     fr
    -1.00
     French
    -0.99
    .fr
    -0.96
    _fr
    -0.96
    fr
    -0.96
    French
    -0.96
    Fr
    -0.95
    POSITIVE LOGITS
    æ»´
    0.26
     Luo
    0.26
     Boca
    0.25
    丣
    0.24
    озв
    0.24
    мел
    0.23
    VAS
    0.23
    å¯IJ
    0.23
    aina
    0.23
     jspb
    0.23
    Activations Density 0.016%

    No Known Activations