© 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. 39841
    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
    zyst
    -0.26
     Zar
    -0.26
     tiled
    -0.25
    åħ±åIJĮåıijå±ķ
    -0.24
    鸢
    -0.24
    ernet
    -0.24
     zar
    -0.24
    yas
    -0.23
    åŁ¹åħ»åѦçĶŁ
    -0.23
     Listing
    -0.23
    POSITIVE LOGITS
    é£İ鼨
    0.32
    没éĴ±
    0.30
    次
    0.28
    éŨ
    0.26
    è´¢ç»ı
    0.26
    \u
    0.26
    éŨå¤ĸ
    0.25
    ÃŃv
    0.24
    tron
    0.24
    verse
    0.24
    Activations Density 4.804%

    No Known Activations

    This feature has no known activations.