© 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. 113114
    Prev
    Next
    INDEX
    Explanations

    Code questions/debugging

    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
    æĸŃ
    -0.31
    容æĺĵ
    -0.30
    å½»åºķ
    -0.29
    itin
    -0.27
     Som
    -0.27
    çªģçł´
    -0.27
    è¾¾åĪ°
    -0.27
    çİ°å·²
    -0.26
    主åĬ¨
    -0.26
    OTS
    -0.26
    POSITIVE LOGITS
    ä»įçĦ¶æĺ¯
    0.51
     still
    0.47
    ä»įå°Ĩ
    0.46
    ä»į
    0.45
    ä»įæĺ¯
    0.45
    ä»įçĦ¶
    0.45
    still
    0.45
    ä¿ĿæĮģ
    0.44
    ä¾ĿçĦ¶æĺ¯
    0.44
     remained
    0.43
    Activations Density 0.003%

    No Known Activations