© 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. 88863
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    éĩįå¿ĥ
    -0.30
    è´µ
    -0.28
    æ¯Ķä¾ĭ
    -0.28
    æŶéĹ´åĴĮ
    -0.27
    æħ¢
    -0.27
    anya
    -0.26
    å±ı
    -0.25
    icina
    -0.25
     cj
    -0.23
    Lou
    -0.23
    POSITIVE LOGITS
    cope
    0.31
    .coordinate
    0.27
    ///<
    0.24
    å¼ĢçĿĢ
    0.24
    æľĿéĺ³
    0.24
     keywords
    0.24
    åĶı
    0.24
     marker
    0.23
     coordinate
    0.23
     symbols
    0.23
    Activations Density 0.086%

    No Known Activations