© 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. 27614
    Prev
    Next
    INDEX
    Explanations

    max, biggest, score, name, ans

    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
    ville
    -0.07
    plin
    -0.07
    æ¸ħæ¸ħ
    -0.07
    æľīåij³
    -0.07
    ArrayOf
    -0.07
     alleg
    -0.06
     sourcing
    -0.06
    åıijå±ķæĶ¹éĿ©å§Ķ
    -0.06
    ä¸Ŀä¸Ŀ
    -0.06
    æ³ķå¾ĭåĴ¨è¯¢
    -0.06
    POSITIVE LOGITS
    uard
    0.08
    çĵ¶é¢Ī
    0.07
    馳
    0.07
    =max
    0.07
    ardy
    0.07
    ÛĮÙĨÙĩ
    0.07
    .Record
    0.07
    |max
    0.07
     rekord
    0.07
    é©°
    0.07
    Activations Density 0.002%

    No Known Activations