© 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. 51693
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
    è·¯ä¸İ
    -0.07
    åįĥæĸ¤
    -0.07
    æŁ»
    -0.07
    åĢĴæĺ¯
    -0.06
    áni
    -0.06
    arkin
    -0.06
    çļĦäººåľ¨
    -0.06
    usin
    -0.06
    amus
    -0.06
    "+
    -0.06
    POSITIVE LOGITS
    urst
    0.08
    fone
    0.08
    ksam
    0.08
    itters
    0.07
    ÉĻcÉĻ
    0.07
    à¹Ģà¸Ĺà¹Īาà¸Ļัà¹īà¸Ļ
    0.07
    éĻIJåĶ®
    0.07
    unft
    0.07
    yti
    0.07
    eroon
    0.07
    Activations Density 0.014%

    No Known Activations