© 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. 18112
    Prev
    Next
    INDEX
    Explanations

    except

    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
    orex
    -0.08
    ög
    -0.08
    oop
    -0.08
    èĻ½çĦ¶çİ°åľ¨
    -0.08
    áĥłáĥIJ
    -0.08
    å¤§æľ¬
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
    æĬ½è±¡
    -0.07
    .Std
    -0.07
    oops
    -0.07
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.11
     olmak
    0.09
    åľ¨åĨħçļĦ
    0.08
    åħ¶é¤ĺ
    0.08
    没æľīåħ¶ä»ĸ
    0.07
    åIJ¦åĪĻ
    0.07
    [^
    0.07
    ãģĤãģ¨ãģ¯
    0.07
    reno
    0.07
    aku
    0.07
    Activations Density 0.137%

    No Known Activations