© 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. 88932
    Prev
    Next
    INDEX
    Explanations

    historical events

    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
    ãģ¬
    -0.26
    çªĹæĪ·
    -0.25
    ç½ijç»ľä¼łæĴŃ
    -0.24
    æŸ
    -0.24
    æīĵè¿Ľ
    -0.23
    æĺ¯æ²¡æľī
    -0.23
    serter
    -0.23
    åİŁæĿ¥
    -0.23
    place
    -0.23
     CSI
    -0.23
    POSITIVE LOGITS
    Ỽ
    0.25
    Structured
    0.24
    structured
    0.24
     barring
    0.24
    dera
    0.23
    åĽĽå¹´
    0.23
     коллекÑĤив
    0.23
     conservative
    0.23
     Dissertation
    0.23
    æĢ»éĩı
    0.23
    Activations Density 0.016%

    No Known Activations