© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    math expressions or code examples

    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
     uncomment
    -0.07
    æ£ł
    -0.07
    å°ıéĽª
    -0.07
    رائ
    -0.07
    åĪĿæģĭ
    -0.06
     emph
    -0.06
    çİ©çļĦ
    -0.06
    iesz
    -0.06
    queue
    -0.06
     Frat
    -0.06
    POSITIVE LOGITS
    erno
    0.07
    neas
    0.07
    mile
    0.07
    hic
    0.07
    ноÑģиÑĤ
    0.07
    sip
    0.07
    ossid
    0.07
    osite
    0.07
    Grand
    0.06
    å¶ĭ
    0.06
    Activations Density 0.006%

    No Known Activations