© 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. 41009
    Prev
    Next
    INDEX
    Explanations

    Measurements and multiplication

    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
     TIMES
    -0.30
    纸ä¸Ĭ
    -0.28
    Meter
    -0.28
    meter
    -0.27
     times
    -0.27
    okia
    -0.26
     ç±
    -0.26
    éĢıè§Ĩ
    -0.25
    oku
    -0.25
    rice
    -0.25
    POSITIVE LOGITS
    æĽ´
    0.33
    æĽ´ä½İ
    0.31
    double
    0.28
    asier
    0.28
    æĽ´å¥½
    0.28
     double
    0.28
    æĽ´æ·±
    0.27
    æĽ´å¼º
    0.27
     triple
    0.27
    Double
    0.26
    Activations Density 0.001%

    No Known Activations