© 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. 38531
    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
    Negative Logits
    ä¸įè§ģäºĨ
    -0.34
     conveying
    -0.28
    ä¸įç®¡ä½ł
    -0.28
    _AST
    -0.28
    ä¿Ŀ驾
    -0.28
    -loving
    -0.27
     ceased
    -0.27
     bleeding
    -0.26
    -readable
    -0.26
    estar
    -0.26
    POSITIVE LOGITS
    æıIJ
    0.32
    äºĴ
    0.31
     å½
    0.30
     ç
    0.30
    éĩı
    0.30
    çĶ¨
    0.30
    æł¸
    0.29
    åıĸ
    0.29
    éĢļè¿ĩ
    0.29
    åĩº
    0.29
    Activations Density 0.809%

    No Known Activations

    This feature has no known activations.