© 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. 11678
    Prev
    Next
    INDEX
    Explanations

    facts About

    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
    اÛģ
    -0.07
    çĽ¸æľĽ
    -0.07
    assel
    -0.07
    ondi
    -0.07
    burg
    -0.06
    ÑĢод
    -0.06
    нев
    -0.06
    اÙĩ
    -0.06
    ä¹łä½ľ
    -0.06
    baugh
    -0.06
    POSITIVE LOGITS
    ulous
    0.10
     facts
    0.09
    ä¸įèĻļ
    0.08
    åĴĮåĽ¾çīĩ
    0.08
    äºĭå®ŀ
    0.08
    ulative
    0.08
    itude
    0.07
    ncio
    0.07
    çļĦäºĭå®ŀ
    0.07
    oj
    0.07
    Activations Density 0.021%

    No Known Activations