© 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. 39175
    Prev
    Next
    INDEX
    Explanations

    latex math notation

    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
    enburg
    -0.07
    ог
    -0.07
    е
    -0.07
    /
    -0.07
     ..."
    -0.07
    ов
    -0.07
    ↵        ↵        ↵
    -0.07
    ogramm
    -0.07
    ÑīноÑģÑĤÑĮ
    -0.07
    enk
    -0.07
    POSITIVE LOGITS
    nya
    0.09
    gle
    0.09
    iasco
    0.09
    iance
    0.09
    ÛĮ
    0.09
    <|box_end|>
    0.08
    Ŀ
    0.08
    èŁĢ
    0.08
    ±
    0.08
    ÑģÑı
    0.08
    Activations Density 0.028%

    No Known Activations