© 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. 52886
    Prev
    Next
    INDEX
    Explanations

    authors, novels, literature

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ç§ijåѦæĬĢæľ¯
    -0.39
    ç§ijæĻ®
    -0.32
    ç§ijå¹»
    -0.28
     science
    -0.27
    NEL
    -0.27
     bás
    -0.26
     Sci
    -0.26
    bang
    -0.26
    ç§ijæĬĢ
    -0.26
     attend
    -0.25
    POSITIVE LOGITS
     sm
    0.29
    ot
    0.29
     CJ
    0.27
    çīĽ
    0.26
    OT
    0.25
     New
    0.25
     Cow
    0.25
     tagging
    0.24
    iki
    0.23
     ra
    0.23
    Activations Density 0.019%

    No Known Activations