© 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. 35-TRANSCODER-HP
    7. 40540
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iens
    -0.30
    iards
    -0.26
    iban
    -0.24
    ixe
    -0.23
    _:*
    -0.23
     nursery
    -0.23
    deaux
    -0.23
    uet
    -0.23
    ipp
    -0.23
     bo
    -0.23
    POSITIVE LOGITS
    说ä¸įåĩº
    0.31
    åĭī强
    0.29
    è½
    0.28
    æ¯ĽåŃĶ
    0.27
    ä¸įå®ļ
    0.26
    then
    0.25
     then
    0.25
    对人ä½ĵ
    0.24
    赶
    0.23
     ache
    0.23
    Activations Density 56.763%

    No Known Activations