© 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. 31-TRANSCODER-HP
    7. 18016
    Prev
    Next
    INDEX
    Explanations

    computer science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     high
    -0.36
    higher
    -0.34
    è¾ĥé«ĺçļĦ
    -0.32
    high
    -0.31
    (low
    -0.31
     higher
    -0.31
     low
    -0.29
     Higher
    -0.29
    æ¯Ķè¾ĥé«ĺ
    -0.29
    Higher
    -0.29
    POSITIVE LOGITS
    å±Ĥ
    0.36
    ONG
    0.33
    層
    0.30
    -layer
    0.30
    å¼Ģå§ĭäºĨ
    0.29
    ong
    0.29
    Layer
    0.28
     layer
    0.28
    ono
    0.27
    ongan
    0.26
    Activations Density 0.925%

    No Known Activations