© 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. 40732
    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
    æľīæĦı
    -0.29
    å½¢
    -0.28
     اÙĦØ£ÙĪ
    -0.27
    çIJĨ
    -0.27
    â
    -0.27
    广
    -0.27
    ä¸Ĭ
    -0.27
    å°ij
    -0.26
    éĩĮ
    -0.26
    çĪ¶
    -0.26
    POSITIVE LOGITS
    _again
    0.27
     dip
    0.26
    è²Ĥ
    0.26
    geh
    0.25
     Dip
    0.25
    ãĤ¯ãĥ©ãĥĸ
    0.25
    çķĻè¨ĢæĿ¿
    0.24
    oola
    0.24
    YPD
    0.24
     assembly
    0.24
    Activations Density 2.260%

    No Known Activations

    This feature has no known activations.