© 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. 9486
    Prev
    Next
    INDEX
    Explanations

    equal to

    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
    ç¨
    -0.08
    ervis
    -0.07
    åı°æµ·
    -0.07
    ä¸ĭåIJĮ
    -0.06
    astro
    -0.06
    اÙĨÛĮ
    -0.06
    ë£Į
    -0.06
    etti
    -0.06
    viet
    -0.06
     аÑģÑģ
    -0.06
    POSITIVE LOGITS
    æĪĸå°ij
    0.08
    peq
    0.08
    æĪĸéĥ¨åĪĨ
    0.08
    æĪĸ缺
    0.07
    ucia
    0.07
    ardy
    0.07
    ustra
    0.07
    çĶ¸
    0.07
    uce
    0.07
    对ä¸Ĭ
    0.07
    Activations Density 0.006%

    No Known Activations