© 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. 39278
    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
    ейÑģÑĤв
    -0.26
    讳
    -0.25
     oportun
    -0.25
    åŁİåİ¿
    -0.25
     opportunity
    -0.25
    FP
    -0.25
    /debug
    -0.24
     Florida
    -0.24
    Portland
    -0.23
    æł¡
    -0.23
    POSITIVE LOGITS
    âĢ¦”↵↵
    0.35
    !.↵↵
    0.30
    .’”↵↵
    0.30
    !”↵↵
    0.30
    .”↵↵↵↵
    0.29
    âĢ¦"↵↵
    0.28
     ..."↵↵
    0.28
     cousins
    0.28
    ram
    0.26
    ’.↵↵
    0.26
    Activations Density 8.891%

    No Known Activations

    This feature has no known activations.