© 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. 112679
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ues
    -0.30
    äºĭ项
    -0.28
    asily
    -0.27
    ãģĵãģ¨ãĤĤ
    -0.25
     material
    -0.24
    ä¸ĢåĽŀäºĭ
    -0.24
    ä¼ĹæīĢ
    -0.24
    ä¼ļéķ¿
    -0.23
    uem
    -0.23
     Wid
    -0.23
    POSITIVE LOGITS
    åģļå¾Ĺ
    0.28
    æīĵå¾Ĺ
    0.24
    éĢģæĿ¥
    0.23
    æĬĬæīĭ
    0.23
     arrang
    0.23
    é¢Ŀ
    0.23
    æ·Ģç²ī
    0.22
    åģļäºĨ
    0.22
    BD
    0.22
    paths
    0.22
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.