© 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. 8204
    Prev
    Next
    INDEX
    Explanations

    have a/some

    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
    çļĦ大éĩı
    -0.08
    æľīæĽ´å¤ļçļĦ
    -0.07
    ors
    -0.07
    æľīæĸ°çļĦ
    -0.07
    åİŁåĪĽä½ľåĵģ
    -0.07
    æľī大éĩı
    -0.07
    ]=-
    -0.07
    æľīæĽ´å¤ļ
    -0.06
    ies
    -0.06
    ä½łçľŁçļĦ
    -0.06
    POSITIVE LOGITS
    yman
    0.08
    天å°Ĭ
    0.08
    LF
    0.08
    çĴĭ
    0.07
    åĵªå®¶
    0.07
    ILO
    0.07
    ç½ĹæĽ¼
    0.07
    Ù¹ÛĮ
    0.07
    |string
    0.07
    éĤij
    0.07
    Activations Density 0.009%

    No Known Activations