© 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. 129389
    Prev
    Next
    INDEX
    Explanations

    code development

    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
    ioned
    -0.31
     accord
    -0.29
    æĹ¢åı¯ä»¥
    -0.26
     ration
    -0.25
    ration
    -0.25
    iders
    -0.25
     instantiated
    -0.25
     chat
    -0.24
     hated
    -0.24
    ivate
    -0.24
    POSITIVE LOGITS
    å¾®
    0.28
    æĺ¯åIJ¦
    0.25
     beginnings
    0.24
    ç¿»
    0.24
    omet
    0.24
    è´«åĽ°æĿij
    0.24
    åįĹ
    0.24
    å¼Ģ头
    0.24
    i
    0.24
    æĦģ
    0.23
    Activations Density 0.003%

    No Known Activations