© 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. 110912
    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
    Negative Logits
    /&
    -0.24
    ndl
    -0.24
    æĬ¥ç¤¾
    -0.24
     andra
    -0.24
     Dess
    -0.24
    å®ļä¹ī
    -0.24
    æī¯
    -0.24
    æĬ¥åijĬæĺ¾ç¤º
    -0.23
    项
    -0.23
     Fry
    -0.23
    POSITIVE LOGITS
    éĢIJæŃ¥
    0.27
     up
    0.26
     *(
    0.26
    rel
    0.25
     rel
    0.25
     banc
    0.25
    ä¸Ģå®ļç¨ĭ度
    0.25
     Part
    0.25
    æŁIJä¸Ģ
    0.25
    ees
    0.24
    Activations Density 0.043%

    No Known Activations

    This feature has no known activations.