© 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. 38564
    Prev
    Next
    INDEX
    Explanations

    6

    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
    ARGIN
    -0.29
    æľĭåıĭ
    -0.28
    azes
    -0.27
     Hir
    -0.25
    渴
    -0.25
    cé
    -0.24
    BOSE
    -0.24
    çijľ
    -0.24
    acted
    -0.24
     avi
    -0.24
    POSITIVE LOGITS
     getWindow
    0.28
     nghi
    0.26
    atcher
    0.24
    shaw
    0.23
    åľ¨å¹¿å·ŀ
    0.23
    åij¨å¹´
    0.23
    é¤į
    0.23
    exampleModal
    0.23
     NSW
    0.23
    æĤ¬å´ĸ
    0.23
    Activations Density 2.550%

    No Known Activations