© 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. 21543
    Prev
    Next
    INDEX
    Explanations

    where variables or symbols

    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
    æ··åIJĪåŀĭ
    -0.08
    æĥħåĨµåĪĨæŀIJ
    -0.08
     somehow
    -0.08
    Assertions
    -0.07
     somewhere
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
    nette
    -0.07
    hoff
    -0.07
    ä¸ļåĬ¡æµģç¨ĭ
    -0.07
    æĮĿ
    -0.07
    POSITIVE LOGITS
     Mellon
    0.07
    iki
    0.07
    unicode
    0.07
    _VISIBLE
    0.07
     Ogg
    0.06
     ÙĪØŃد
    0.06
    å°±æĺ¯äºĨ
    0.06
     اخت
    0.06
    ختÙĩ
    0.06
    ukse
    0.06
    Activations Density 0.008%

    No Known Activations