© 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. 33-TRANSCODER-HP
    7. 54808
    Prev
    Next
    INDEX
    Explanations

    scientific context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    italic
    -0.27
    /OR
    -0.26
     /*#__
    -0.25
    acist
    -0.25
     writ
    -0.24
    æĺ¯æĪij
    -0.24
    uel
    -0.24
    sigma
    -0.23
    qr
    -0.23
    [q
    -0.23
    POSITIVE LOGITS
     oppos
    0.34
     opposite
    0.27
    _SOURCE
    0.27
    Opp
    0.25
    дон
    0.25
     utilities
    0.25
     plate
    0.24
    èIJĿåįľ
    0.24
    _collections
    0.24
    ivor
    0.24
    Activations Density 0.015%

    No Known Activations