© 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. 40075
    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
    SC
    -0.30
    -bodied
    -0.29
    æł¡
    -0.26
    éĿ¢åŃĶ
    -0.26
    SSF
    -0.25
    .arguments
    -0.25
     fixed
    -0.25
    arent
    -0.25
    åĽºå®ļ
    -0.24
    çİĭåºľ
    -0.24
    POSITIVE LOGITS
     Glas
    0.23
    publication
    0.23
    çĭłçĭł
    0.23
    quests
    0.23
    positories
    0.23
    OCK
    0.23
    为æѤ
    0.23
    çĽ¸å·®
    0.23
    許
    0.23
    tile
    0.23
    Activations Density 0.110%

    No Known Activations

    This feature has no known activations.