© 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. 129074
    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
     unless
    -0.27
    Flag
    -0.26
     ca
    -0.26
    ché
    -0.26
    zac
    -0.25
    SEC
    -0.24
    CE
    -0.24
     Flag
    -0.24
    Unless
    -0.24
    Flags
    -0.23
    POSITIVE LOGITS
    remely
    0.27
    éĢļä¿Ĺ
    0.27
     uniformly
    0.25
    çļĦæł·åŃIJ
    0.25
    工夫
    0.25
    ä¸Ģä¸ĭåŃIJå°±
    0.24
    ingly
    0.24
    èµ·æŃ¥
    0.24
    .getList
    0.24
    å¤ļå±Ĥ次
    0.24
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.