© 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. 32706
    Prev
    Next
    INDEX
    Explanations

    Sapience, Suntiger, Beta, Advanced

    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
     porr
    -0.08
    -%
    -0.08
    >Title
    -0.08
    为å®ĺ
    -0.07
    .nasa
    -0.07
    вÑı
    -0.07
    .appspot
    -0.07
    ingo
    -0.07
    upal
    -0.07
    ä¿ĿéĻ©éĩij
    -0.07
    POSITIVE LOGITS
     prec
    0.07
    çłģé¾Ħ
    0.07
     who
    0.06
    åij¼åĴĮ
    0.06
    ä¸ŃæĸĩåIJį
    0.06
     avatar
    0.06
     vạn
    0.06
     Consortium
    0.06
     mint
    0.06
     cy
    0.06
    Activations Density 0.299%

    No Known Activations