© 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. 40416
    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
    Interpreter
    -0.29
     Fram
    -0.28
     fishes
    -0.24
    æĪijçľĭ
    -0.24
     Bast
    -0.24
     pol
    -0.23
    reeting
    -0.23
    lexer
    -0.23
    interpreter
    -0.23
     vets
    -0.23
    POSITIVE LOGITS
    çļĦæĢĿæĥ³
    0.27
    åij³
    0.26
    èĢ½
    0.26
    ìĸ¸
    0.25
    tÃŃ
    0.25
    åĬĽè¿ĺæĺ¯
    0.25
    太å¤ļ
    0.25
    ä¿¡ä»»
    0.25
    bear
    0.25
    çļĦåķĨåĵģ
    0.25
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.