© 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. 62744
    Prev
    Next
    INDEX
    Explanations

    Directions

    np_max-act · gemini-2.0-flash
    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
    许åı¯è¯ģ
    -0.29
    ç¼ĸ
    -0.26
    饽
    -0.25
    è¡Įä¸ļåıijå±ķ
    -0.25
     khảo
    -0.24
     Christ
    -0.24
    çļĦéĹ®é¢ĺ
    -0.24
    bish
    -0.24
    .ArgumentParser
    -0.24
    æľīä½ķ
    -0.23
    POSITIVE LOGITS
     Abs
    0.27
    -anchor
    0.27
    ðŁĻĤ
    0.26
     caz
    0.25
     travelling
    0.25
    изаÑĨии
    0.25
     Vict
    0.24
    æĹħè¡Į
    0.24
    姥
    0.24
    鬥
    0.24
    Activations Density 14.382%

    No Known Activations