© 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. 39633
    Prev
    Next
    INDEX
    Explanations

    citations with brackets

    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
    åľ¨åį³
    -0.07
    åĴĮå¹³
    -0.06
    平平
    -0.06
    ród
    -0.06
    mart
    -0.06
     Paz
    -0.06
    _override
    -0.06
    Scoped
    -0.06
    认è¯ĨäºĨ
    -0.06
     TEK
    -0.06
    POSITIVE LOGITS
    ì²ĺ
    0.08
    /mit
    0.07
    ahr
    0.07
    toa
    0.07
    çīĪæĿĥ声æĺİ
    0.07
    stens
    0.07
     seter
    0.07
     rác
    0.07
    è¾ĥæĹ©
    0.07
    ayload
    0.07
    Activations Density 0.150%

    No Known Activations