© 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. 20-TRANSCODER-HP
    7. 142622
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    vic
    -0.25
    ä¸ĩéĩĮ
    -0.25
    chw
    -0.25
    å´©
    -0.24
     vic
    -0.24
    raz
    -0.23
    Ñĵ
    -0.23
     d
    -0.23
    äº
    -0.23
     Clears
    -0.23
    POSITIVE LOGITS
    ston
    0.28
    /MPL
    0.27
    ENU
    0.27
    âĢ¦the
    0.26
    umer
    0.26
    cul
    0.26
    звÑĥÑĩ
    0.25
    æ¯ıä½į
    0.24
    èĢ³è¾¹
    0.24
    tré
    0.24
    Activations Density 0.766%

    No Known Activations

    This feature has no known activations.