© 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. 94885
    Prev
    Next
    INDEX
    Explanations

    code/data entries

    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
    Negative Logits
    Query
    -0.29
    oland
    -0.29
    APON
    -0.29
    _QUERY
    -0.29
    æŁ¥è¯¢
    -0.28
     Query
    -0.27
    ani
    -0.27
    _query
    -0.27
    \Query
    -0.27
    ANI
    -0.27
    POSITIVE LOGITS
    enheim
    0.28
    衾
    0.27
     dependent
    0.27
    ients
    0.27
     aerial
    0.26
    æ¡Įä¸Ĭ
    0.25
    acters
    0.25
    æ¡Į
    0.25
     linked
    0.25
     reductions
    0.25
    Activations Density 0.103%

    No Known Activations