© 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. 21024
    Prev
    Next
    INDEX
    Explanations

    grant to

    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
    åħ·æľīä¸Ģå®ļçļĦ
    -0.07
    :)
    -0.06
    æĭ¥æľīä¸Ģ个
    -0.06
    ikian
    -0.06
    以åıĬåIJĦç§į
    -0.06
    åĮħåIJ«äºĨ
    -0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    å«£
    -0.06
    æĺŃåĴĮ
    -0.06
     [*
    -0.06
    POSITIVE LOGITS
    åı¯ä¸º
    0.09
    è¿ĻåĽŀ
    0.09
    ç»ĦåĽ¾
    0.08
    ï½ľ
    0.08
    åı¯æ»¡è¶³
    0.08
     amid
    0.08
    åĨįæ·»
    0.08
    丨
    0.08
    éĽ£æĢª
    0.08
     dziÅĽ
    0.08
    Activations Density 1.205%

    No Known Activations