© 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. 55528
    Prev
    Next
    INDEX
    Explanations

    apparent, observed, or measured

    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
    jenigen
    -0.10
    apore
    -0.10
    icidad
    -0.10
    ÙħÙĨد
    -0.09
     ÐŁÐ¾Ð¿ÑĢо
    -0.09
    ÐĸÐĶ
    -0.09
    icidade
    -0.09
    imler
    -0.08
     ÐĴÑģÑĤÑĢе
    -0.08
    ameran
    -0.08
    POSITIVE LOGITS
    ment
    0.08
    à¸ģารà¸ĵà¹Į
    0.07
    راض
    0.07
    edly
    0.07
    nen
    0.07
    o
    0.07
    emente
    0.06
    uguay
    0.06
    ãģªãģĮãĤī
    0.06
    æĹłè¸ª
    0.06
    Activations Density 0.080%

    No Known Activations