© 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. 22-TRANSCODER-HP
    7. 86936
    Prev
    Next
    INDEX
    Explanations

    Scientific Research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èįļ
    -0.26
     catchError
    -0.25
    é¦Ļ
    -0.25
    ä»Ģä¹Īä¸ľè¥¿
    -0.25
    ìĹ½
    -0.25
     Kỳ
    -0.24
     pelÃŃcula
    -0.24
    _MATH
    -0.24
    é±¼
    -0.23
     Poll
    -0.23
    POSITIVE LOGITS
    æĺ¯ä¸Ģ项
    0.29
    ä¸Ģ缴æĺ¯
    0.27
    *</
    0.26
     blind
    0.26
     seldom
    0.26
    abilidade
    0.26
    åħ´èµ·
    0.25
    è¿ijå¹´æĿ¥
    0.25
    ÈĽi
    0.25
    æĹ¢è¦ģ
    0.25
    Activations Density 0.106%

    No Known Activations