© 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. 34443
    Prev
    Next
    INDEX
    Explanations

    parts of things

    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
    -ish
    -0.07
    arser
    -0.07
    ãģ¹ãģı
    -0.07
    éļĽãģ¯
    -0.06
    izia
    -0.06
    aily
    -0.06
    ooky
    -0.06
    ÑīеÑĢ
    -0.06
    tober
    -0.06
     airs
    -0.06
    POSITIVE LOGITS
    åĴĮèī¯å¥½çļĦ
    0.09
    åĴĮ丰å¯ĮçļĦ
    0.09
    æĦıåij³çĿĢ
    0.08
    uto
    0.08
    ä½Ĩèĩ³å°ij
    0.08
    为åīįæıIJ
    0.08
    REL
    0.07
    åīįæıIJä¸ĭ
    0.07
     despite
    0.07
    ãģªãģĮãĤīãĤĤ
    0.07
    Activations Density 0.297%

    No Known Activations