© 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. 47333
    Prev
    Next
    INDEX
    Explanations

    punctuation following words like 'evident'

    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
    еÑģо
    -0.07
    éĿĴæĺ¥çļĦ
    -0.07
    æľī人说
    -0.07
    æĺ¯åħ¨çIJĥ
    -0.07
    ousel
    -0.07
    rou
    -0.06
    æľīè´£
    -0.06
    ÑģпекÑĤи
    -0.06
     Kemp
    -0.06
    ä¸ĭåŀĤ
    -0.06
    POSITIVE LOGITS
    èijĨ
    0.08
    à¹Ĭà¸ĩ
    0.07
    arella
    0.07
     nô
    0.07
    lick
    0.07
    maks
    0.07
    æľĢåIJİæĺ¯
    0.07
    isz
    0.07
    å½±
    0.07
    ÏĦαν
    0.07
    Activations Density 0.049%

    No Known Activations