© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42547
    Prev
    Next
    INDEX
    Explanations

    letter options (a, b, c) followed 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
    gäng
    -0.08
    arness
    -0.08
    criptor
    -0.08
    ).__
    -0.07
    纪è¦ģ
    -0.07
    主çļĦ
    -0.07
    #__
    -0.07
     piv
    -0.07
    é£İ顺
    -0.07
    egend
    -0.07
    POSITIVE LOGITS
    ï¼ļ
    0.07
    opo
    0.07
     vs
    0.06
     Hubb
    0.06
    OutOfBoundsException
    0.06
    prise
    0.06
    Ñĥк
    0.06
    ï¸ı
    0.06
    odaw
    0.06
    apolis
    0.06
    Activations Density 0.004%

    No Known Activations