© 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. 17902
    Prev
    Next
    INDEX
    Explanations

    References to God

    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
    eking
    -0.29
    å®ī
    -0.29
    ysz
    -0.29
     Ant
    -0.28
    anness
    -0.26
    anel
    -0.26
    vic
    -0.26
     Mention
    -0.25
    éĢįéģ¥
    -0.25
    vro
    -0.24
    POSITIVE LOGITS
    umin
    0.27
    PathComponent
    0.25
    _grid
    0.25
     ç
    0.25
    _deploy
    0.24
     capital
    0.23
    ìŀ¡
    0.23
    æ±²
    0.23
    ght
    0.23
    åįģåĽĽæĿ¡
    0.23
    Activations Density 0.076%

    No Known Activations