© 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. 23564
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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|>
    -0.06
     prolonged
    -0.06
    leston
    -0.06
    ÃŃk
    -0.06
    æīĢä»¥ä½ł
    -0.06
    çĤİ
    -0.06
    HT
    -0.06
     Bates
    -0.06
     å¼ķçĶ¨
    -0.06
    ÐIJÐŁ
    -0.06
    POSITIVE LOGITS
    reopen
    0.08
    >tag
    0.07
     tá»ı
    0.07
    uggling
    0.07
    çļĦä¸ĵä¸ļ
    0.07
    uggest
    0.07
    ãģ¨ãģ¯ãģĦãģĪ
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    craft
    0.07
    CDATA
    0.07
    Activations Density 0.000%

    No Known Activations