© 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. 54471
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    å°±æĺ¯ä¸ºäºĨ
    -0.30
    าà¸Ļ
    -0.29
    bred
    -0.28
     refined
    -0.28
    磶
    -0.27
    é²
    -0.26
     refining
    -0.25
    ç©·
    -0.25
     brid
    -0.24
    è·³åĩº
    -0.24
    POSITIVE LOGITS
    deliver
    0.28
     Handling
    0.27
    /catalog
    0.25
    bour
    0.25
    åĵī
    0.25
     Salem
    0.25
     Hardcover
    0.24
    лан
    0.24
    lan
    0.24
     recon
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.