© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    explaining solutions and methods

    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
     supposedly
    -0.08
    å®ŀéĻħåĩºåıij
    -0.07
    enticate
    -0.07
    ÙıÙĪ
    -0.07
    ystems
    -0.07
    лке
    -0.07
    odate
    -0.07
    igts
    -0.06
    çļĦèĥĮåIJİ
    -0.06
    å½ĵçĦ¶
    -0.06
    POSITIVE LOGITS
     accordingly
    0.11
     berupa
    0.09
     details
    0.08
    æĥħåĨµè¯´æĺİ
    0.08
    è¯ģæį®è¯ģæĺİ
    0.08
     examples
    0.08
    ä¸įå®ĮçļĦ
    0.07
    æĺİç¡®çļĦ
    0.07
     breakdown
    0.07
     ìĺĪ를
    0.07
    Activations Density 0.023%

    No Known Activations