© 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. 31-TRANSCODER-HP
    7. 19894
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     cms
    -0.27
    |[
    -0.27
    LU
    -0.26
    ,eg
    -0.25
    ictured
    -0.25
    mens
    -0.25
    navbarDropdown
    -0.24
    CMS
    -0.23
    .ce
    -0.23
    äºİä¸Ģä½ĵçļĦ
    -0.23
    POSITIVE LOGITS
    次æķ°
    0.28
    ä¸įåĬ¨
    0.28
    ç³»ç»Ł
    0.28
    æݧåĪ¶ç³»ç»Ł
    0.26
    å©´
    0.25
     Casc
    0.24
    à¹ģรà¸ģ
    0.24
    æķ¬
    0.24
     lifetime
    0.24
     shares
    0.24
    Activations Density 1.234%

    No Known Activations

    This feature has no known activations.