© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39608
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     absolut
    -0.25
    åĴĮæĬĢæľ¯
    -0.25
    iggins
    -0.24
    weeks
    -0.23
    æĸ°æĿIJæĸĻ
    -0.23
     gladly
    -0.23
    羣çIJĨ
    -0.23
    asures
    -0.23
    expanded
    -0.23
    ffield
    -0.23
    POSITIVE LOGITS
    lsi
    0.25
    åĨįåĪ°
    0.24
     Magical
    0.24
    .getFirst
    0.23
    }\.[
    0.23
     Fireplace
    0.23
    ãĥīãĥ©ãĥŀ
    0.23
    .Sequential
    0.22
     Rift
    0.22
    ToLocal
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.