© 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. 110910
    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
     redund
    -0.25
    çĭĢ
    -0.25
    jÄĻ
    -0.25
    è¶Ĭ
    -0.25
     divers
    -0.24
    /logging
    -0.24
     drainage
    -0.24
    ä¸įåıĹ
    -0.24
    ä¸Ńæłĩ
    -0.24
    æıı
    -0.23
    POSITIVE LOGITS
    çŁ¥è¯ĨåĪĨåŃIJ
    0.26
    侧éĿ¢
    0.26
    馨
    0.25
     Appe
    0.25
     KG
    0.25
     Abbott
    0.25
    pole
    0.25
    绣ä¸Ģ
    0.25
     ANN
    0.25
    _pwd
    0.25
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.