© 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. 12-TRANSCODER-HP
    7. 23482
    Prev
    Next
    INDEX
    Explanations

    ern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç½ķ
    -0.26
    he
    -0.25
    iards
    -0.24
    æľĢ好çļĦ
    -0.24
    æ¡£
    -0.24
    ologi
    -0.24
    æ²ŁéĢļ
    -0.23
    -catching
    -0.23
     Fra
    -0.23
    hev
    -0.23
    POSITIVE LOGITS
    稷
    0.26
    åį®
    0.25
    æĸ°æµªè´¢ç»ı
    0.25
    _mob
    0.25
     circular
    0.24
    sap
    0.24
    acey
    0.24
     cir
    0.24
    åįĴ
    0.24
     Brick
    0.24
    Activations Density 0.108%

    No Known Activations