© 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. 60476
    Prev
    Next
    INDEX
    Explanations

    css font-size and center alignment

    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
    memberof
    -0.08
    ÑĤина
    -0.08
    abant
    -0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    -0.07
    alow
    -0.07
    ä¸įè°ĥ
    -0.07
    ä½İä»·
    -0.07
     маÑģÑģо
    -0.07
    éĽªçĻ½çļĦ
    -0.07
    æĹłæįŁ
    -0.07
    POSITIVE LOGITS
    ä¸Ń大
    0.09
    äºijé¾Ļ
    0.06
    akk
    0.06
    SVG
    0.06
    udz
    0.06
     emph
    0.06
     text
    0.06
    å¹´å¢ŀéķ¿
    0.06
     chained
    0.06
    ä¸Ģ身
    0.06
    Activations Density 0.025%

    No Known Activations