© 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. 60573
    Prev
    Next
    INDEX
    Explanations

    quality or state

    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
     essentially
    -0.13
     presumably
    -0.13
     basically
    -0.13
     possibly
    -0.12
     apparently
    -0.11
    åı¯èĥ½çļĦ
    -0.10
     evidently
    -0.10
     Essentially
    -0.10
    possibly
    -0.10
     potentially
    -0.10
    POSITIVE LOGITS
     бÑĭваеÑĤ
    0.13
    å¾Īå°ijæľī
    0.10
    缴æİ¥æĪĸ
    0.10
     algún
    0.09
     nowadays
    0.09
     suele
    0.09
    以ä¸ĭåĩłç§į
    0.09
     бÑĭваÑİÑĤ
    0.09
    æĺ¯ä¸įä¼ļ
    0.09
    缴æİ¥æĪĸéĹ´æİ¥
    0.09
    Activations Density 0.662%

    No Known Activations