© 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. 30284
    Prev
    Next
    INDEX
    Explanations

    care for

    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
    å½¢çļĦ
    -0.10
    ional
    -0.09
    ิà¸ķิ
    -0.08
    nalité
    -0.08
    ively
    -0.08
    à¸į
    -0.08
    ectomy
    -0.08
    æľĿæ°Ķ
    -0.08
    ä¹ĭ交
    -0.08
    áĥ£áĥłáĥĺ
    -0.08
    POSITIVE LOGITS
    æĢ»ç½²
    0.08
    lessness
    0.08
    ime
    0.08
    liness
    0.08
    fusion
    0.07
    iche
    0.07
    igned
    0.07
    æĹłå¾®ä¸įèĩ³
    0.07
    ThreadPool
    0.07
    æľīåĬł
    0.07
    Activations Density 0.046%

    No Known Activations