© 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. 19245
    Prev
    Next
    INDEX
    Explanations

    regards, regarded, subjective, Kwan

    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
    scape
    -0.10
    нок
    -0.10
    ington
    -0.09
    ئا
    -0.09
    åĽ½å¼º
    -0.09
    åħ³å¤´
    -0.08
    گاÙĩÛĮ
    -0.08
    tlement
    -0.08
    agonal
    -0.08
    åĵģçļĦ
    -0.08
    POSITIVE LOGITS
    ¥
    0.09
    zinho
    0.08
    áŁĭ
    0.08
    itional
    0.07
    ษà¹Į
    0.07
    antum
    0.07
    ľ
    0.07
    heed
    0.07
    Ñıд
    0.07
    enheim
    0.07
    Activations Density 0.013%

    No Known Activations