© 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. 97367
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    æłĩå¿ĹçĿĢ
    -0.28
    spar
    -0.28
    被åĪ¤
    -0.27
    usch
    -0.26
    忽
    -0.25
    éĹ³
    -0.24
    åĿıäºĨ
    -0.24
    ä¸Ģ个æĺ¯
    -0.24
     Hud
    -0.24
    é¹Ĺ
    -0.24
    POSITIVE LOGITS
     reservations
    0.27
    ä¸ĢçĤ¹åĦ¿
    0.25
     Sek
    0.25
    ·æĸ°
    0.25
    clang
    0.24
    nement
    0.23
     sec
    0.23
    éĿĸ
    0.23
    eward
    0.23
    aring
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.