© 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. 32-TRANSCODER-HP
    7. 43876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĭ¬ç«ĭ
    -0.30
     neighbors
    -0.27
    -independent
    -0.26
     independ
    -0.26
     neighbours
    -0.26
     subjects
    -0.25
     independently
    -0.25
     individuals
    -0.25
     independents
    -0.24
    cade
    -0.24
    POSITIVE LOGITS
     Sleeping
    0.28
    è·ijäºĨ
    0.28
    è·ij
    0.26
    /commons
    0.25
    欢è¿İæĤ¨
    0.25
    æ²¹çĥŁ
    0.25
     kickoff
    0.25
    èĢ¦
    0.24
    gain
    0.24
    è¿Ļç¯ĩæĸĩç«ł
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.