© 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. 9-TRANSCODER-HP
    7. 29915
    Prev
    Next
    INDEX
    Explanations

    weather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rac
    -0.29
    rup
    -0.29
    _Public
    -0.27
     freedom
    -0.27
    -public
    -0.26
     outer
    -0.26
    wood
    -0.26
     kinds
    -0.26
    æ»ĭåij³
    -0.26
    Hand
    -0.25
    POSITIVE LOGITS
    enko
    0.32
     onLoad
    0.29
    纵åIJij
    0.25
    ULL
    0.25
    ItemImage
    0.24
    ç½ijç»ľä¼łæĴŃ
    0.24
    å½ĵä¹ĭ
    0.24
    æ·±åħ¥äººå¿ĥ
    0.24
    èݽ
    0.24
     Gems
    0.24
    Activations Density 1.083%

    No Known Activations