© 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. 48984
    Prev
    Next
    INDEX
    Explanations

    example clarifying questions

    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
    olean
    -0.08
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    -0.07
    äºĮåįģäºĮ
    -0.07
    缸å½ĵçļĦ
    -0.07
    borough
    -0.07
    irse
    -0.07
    keit
    -0.07
    ÛĮرÛĮ
    -0.06
    idable
    -0.06
    (selector
    -0.06
    POSITIVE LOGITS
    举个
    0.10
    举个ä¾ĭåŃIJ
    0.10
    ä¾ĭåŃIJ
    0.10
     ìĺĪ를
    0.09
    çļĦä¾ĭåŃIJ
    0.09
     example
    0.09
    举ä¾ĭ
    0.08
    Example
    0.08
     Example
    0.08
    å°±æĭ¿
    0.08
    Activations Density 0.037%

    No Known Activations