© 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. 54786
    Prev
    Next
    INDEX
    Explanations

    code or license

    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
    ad
    -0.28
    åŃĽ
    -0.27
    ci
    -0.26
    bi
    -0.26
    æ¯Ķäºļ
    -0.25
    çĶŁçī©åѦ
    -0.25
     snapping
    -0.25
    Geom
    -0.24
    <option
    -0.24
    HAM
    -0.24
    POSITIVE LOGITS
    .Content
    0.30
     verw
    0.28
     process
    0.28
    ä¸ºæł¸å¿ĥ
    0.27
     centre
    0.27
    ErrorHandler
    0.26
    è¿Ļéĥ¨åĪĨ
    0.26
     centres
    0.26
    è¿ĩç¨ĭ
    0.26
     recalls
    0.25
    Activations Density 0.004%

    No Known Activations