© 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. 13970
    Prev
    Next
    INDEX
    Explanations

    question marks and colons

    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
    ĩ´
    -0.08
    ensos
    -0.08
    ynth
    -0.08
    elang
    -0.08
    arding
    -0.07
    شر
    -0.07
     azért
    -0.07
    æĬĺä¸į
    -0.07
    åĽłä¸ºè¿Ļ个
    -0.07
    UED
    -0.07
    POSITIVE LOGITS
    ÑĨа
    0.07
    åį³çĶ¨
    0.07
    apor
    0.07
    cte
    0.07
    rather
    0.07
     rather
    0.07
    ä¸īéĥ¨æĽ²
    0.06
    èĢĮéĿŀ
    0.06
    apers
    0.06
    ildo
    0.06
    Activations Density 0.339%

    No Known Activations