© 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. 65296
    Prev
    Next
    INDEX
    Explanations

    aims, objective, action, summary, campaign

    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
    åºı
    -0.08
     particuliers
    -0.07
    вно
    -0.07
    itoral
    -0.07
    ç¡®
    -0.07
    转载请
    -0.07
    vog
    -0.07
    اÙĤات
    -0.07
    _finalize
    -0.07
    endi
    -0.07
    POSITIVE LOGITS
     rationale
    0.09
    dera
    0.09
    se
    0.08
    ationale
    0.08
    æīĢåıĹ
    0.08
    ç¼ĺçĶ±
    0.08
    pros
    0.07
     ÑģÑĥÑĤÑĮ
    0.07
    åİŁçIJĨ
    0.07
    çļĦä¾Ŀæį®
    0.07
    Activations Density 0.218%

    No Known Activations