© 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. 64686
    Prev
    Next
    INDEX
    Explanations

    multiple or divisible by

    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
    åįķèĸĦ
    -0.09
    代ä¹ĭ
    -0.08
    妥åĸĦä¿Ŀ管
    -0.07
    gam
    -0.07
    exual
    -0.07
    eus
    -0.07
    ä¸İçİ°å®ŀ
    -0.07
    resco
    -0.07
    itta
    -0.07
    ä¹ĭäºĮ
    -0.07
    POSITIVE LOGITS
    umbs
    0.08
    uhan
    0.07
    æķ´
    0.07
     unlucky
    0.07
     Reinh
    0.07
     multiples
    0.07
    omin
    0.07
    ponsor
    0.07
     divisible
    0.07
    éĿŀæ´²
    0.07
    Activations Density 0.008%

    No Known Activations