© 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. 11636
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
    edor
    -0.08
    ä¸ĩå¹´
    -0.07
    estu
    -0.07
    اÙĪر
    -0.07
    vad
    -0.07
    :;"
    -0.07
    -elected
    -0.07
    ìł
    -0.07
    tero
    -0.07
     Locator
    -0.07
    POSITIVE LOGITS
    éĴĪ对ä¸įåIJĮ
    0.06
    sortable
    0.06
    ızı
    0.06
    ween
    0.06
    è¯ħ
    0.06
    äºĨåĩłä¸ª
    0.06
    æı©
    0.06
    azzi
    0.06
     Equ
    0.06
    atta
    0.06
    Activations Density 0.226%

    No Known Activations