© 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. 30652
    Prev
    Next
    INDEX
    Explanations

    common document sections

    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
    ä½įåľ¨
    -0.07
    ASH
    -0.06
    çĶŁåľ¨
    -0.06
    ä¸įèĥ½è¢«
    -0.06
    =UTF
    -0.06
    å°±æĺ¯ä¸Ģ个
    -0.06
    halb
    -0.06
    代çłģå¦Ĥä¸ĭ
    -0.06
    æīįèĥ½åľ¨
    -0.06
     pa
    -0.06
    POSITIVE LOGITS
    noticed
    0.09
    inho
    0.08
     Ñĥпомина
    0.08
    notice
    0.08
    ccione
    0.08
    çļĦä¸Ģçŀ¬éĹ´
    0.08
     nanti
    0.08
     disebutkan
    0.08
     Noticed
    0.08
    顺便
    0.08
    Activations Density 0.120%

    No Known Activations