© 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. 24-TRANSCODER-HP
    7. 149284
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¹´ä¸ŃåĽ½
    -0.33
    ÙĪات
    -0.28
    æ´±
    -0.27
    MMC
    -0.26
     Kramer
    -0.25
    PACK
    -0.25
    éĴ³
    -0.25
    INAL
    -0.25
    ç´
    -0.25
    posted
    -0.25
    POSITIVE LOGITS
     //////////////////////////////////////////////////////////////////////
    0.27
    ://'
    0.26
    WindowSize
    0.26
    éļ¶å±ŀ
    0.25
    å±ķ
    0.25
    \\
    0.24
    éĻªä¼´
    0.24
    羣çIJĨ
    0.24
    .TextAlignment
    0.24
    å¿Ĺ
    0.24
    Activations Density 0.923%

    No Known Activations

    This feature has no known activations.