© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22391
    Prev
    Next
    INDEX
    Explanations

    tooth decay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <|box_end|>
    -0.10
    徨
    -0.08
    gaard
    -0.08
    azer
    -0.08
    æľ¬æĸĩæĿ¥èĩª
    -0.08
    à¸Ħà¹Į
    -0.08
    å°ĶçļĦ
    -0.07
    istol
    -0.07
    cret
    -0.07
    дон
    -0.07
    POSITIVE LOGITS
    paste
    0.08
    çīĻ
    0.08
    é¾Ī
    0.08
    LESS
    0.07
    齿
    0.07
    çīĻ齿
    0.07
     enamel
    0.07
     мÑĥд
    0.07
    zah
    0.07
    รัà¸Ļ
    0.07
    Activations Density 0.030%

    No Known Activations