© 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. 112974
    Prev
    Next
    INDEX
    Explanations

    diagnosis

    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
    å¾Ĵ
    -0.27
    inkle
    -0.25
    lds
    -0.24
    æĺ§
    -0.24
    éĽĨåIJĪ
    -0.23
    念
    -0.23
    æĿ¥ä¸įåıĬ
    -0.23
     BEST
    -0.23
    座ä½į
    -0.23
     Styles
    -0.23
    POSITIVE LOGITS
    },'
    0.25
    rud
    0.24
    ertest
    0.24
    achu
    0.23
    çīĮ
    0.23
     pros
    0.23
    sequent
    0.23
    ä¹ĭ声
    0.23
    _Method
    0.23
    yı
    0.23
    Activations Density 0.005%

    No Known Activations