© 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. 25978
    Prev
    Next
    INDEX
    Explanations

    quotation marks and delimiters

    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
     TÃī
    -0.08
    igr
    -0.07
    ¯¯
    -0.07
    aires
    -0.07
    raga
    -0.07
    á»Ļt
    -0.07
     poku
    -0.07
    reja
    -0.07
    å²ļ
    -0.07
    ooter
    -0.07
    POSITIVE LOGITS
    纳æĸ¯
    0.08
    åĽĽäºĶ
    0.07
    olver
    0.07
    -controls
    0.07
    abcdefghijklmnopqrstuvwxyz
    0.07
    intis
    0.07
    ì¶ķ
    0.07
     Schles
    0.07
    交æµģåŃ¦ä¹ł
    0.07
    ://%
    0.06
    Activations Density 0.079%

    No Known Activations