© 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. 27-TRANSCODER-HP
    7. 9830
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    imiter
    -0.26
    ÂŃing
    -0.26
    ä¿¡æģ¯åıijå¸ĥ
    -0.25
    apur
    -0.25
    -layout
    -0.24
    rium
    -0.24
    èµĦæºIJéħįç½®
    -0.24
    dsn
    -0.24
    _Entry
    -0.24
    ä¸ī个æľĪ
    -0.24
    POSITIVE LOGITS
    cc
    0.28
    头æĻķ
    0.27
    lov
    0.27
    aris
    0.25
    éĩįå·¥
    0.24
    æīķ
    0.24
     lov
    0.23
    Composite
    0.23
    æłĩ
    0.23
    头ä¸Ĭ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.