© 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. 30-TRANSCODER-HP
    7. 96863
    Prev
    Next
    INDEX
    Explanations

    pulmonary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bet
    -0.30
     Bet
    -0.29
     declar
    -0.28
    æĿ¾
    -0.27
     Beta
    -0.26
    å±Ī
    -0.25
     boards
    -0.25
    .Style
    -0.25
    å´©
    -0.25
    åģ¥
    -0.25
    POSITIVE LOGITS
    mares
    0.29
    bjerg
    0.28
    æ¢Ĺ
    0.28
    å¿ĥ头
    0.28
    arium
    0.28
    opyright
    0.28
    ahead
    0.27
     terrace
    0.26
    ToEnd
    0.26
    ç¦
    0.26
    Activations Density 0.786%

    No Known Activations