© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50121
    Prev
    Next
    INDEX
    Explanations

    by step

    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
    ources
    -0.10
    'http
    -0.09
     ÐĴÑģÑĤÑĢе
    -0.09
     ÐŁÐ¾Ð¿ÑĢо
    -0.09
    伯æģ©
    -0.09
     Сооб
    -0.09
    æ·±æľī
    -0.09
     ÐĴедÑĥ
    -0.09
    KeyType
    -0.08
    activex
    -0.08
    POSITIVE LOGITS
    -
    0.07
    :
    0.07
    ged
    0.07
    )):
    0.06
    itz
    0.06
    !
    0.06
    à¸ģà¹ĩà¸ķาม
    0.06
    **:
    0.06
    zi
    0.06
    $:
    0.06
    Activations Density 0.002%

    No Known Activations