© 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. 19425
    Prev
    Next
    INDEX
    Explanations

    alternative characters

    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
    娥
    -0.08
    nown
    -0.08
    _runtime
    -0.08
    å¸ĥå±ĢåĴĮ
    -0.07
    æĥ³äºĨè§£æĽ´å¤ļ
    -0.07
    ä¸Ńè¶ħ
    -0.07
    ×ķס
    -0.07
    artes
    -0.07
    ney
    -0.07
    hev
    -0.07
    POSITIVE LOGITS
    æ¯Ķä¾ĭ为
    0.08
    åī²åIJĪ
    0.08
    åĽĽç§į
    0.07
    åĢįçļĦ
    0.07
    çĶµèį·
    0.07
    HIR
    0.07
    çķ¥å¸¦
    0.07
    两ç§į
    0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯
    0.07
    ä¼´
    0.07
    Activations Density 0.001%

    No Known Activations