© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130561
    Prev
    Next
    INDEX
    Explanations

    Python code "__future__ import"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    chest
    -0.28
    kwargs
    -0.26
     MSD
    -0.24
    pitch
    -0.24
    argin
    -0.24
    ä¸ī个æľĪ
    -0.23
     action
    -0.23
     periodic
    -0.23
     Monthly
    -0.23
     Painting
    -0.23
    POSITIVE LOGITS
     modern
    0.74
    çݰ代
    0.71
    çݰ代åĮĸ
    0.61
     moderne
    0.60
    çı¾ä»£
    0.59
     Modern
    0.57
    modern
    0.56
    Modern
    0.56
    æĹ¶ä»£
    0.54
    çݰ代社ä¼ļ
    0.53
    Activations Density 0.007%

    No Known Activations