© 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. 42566
    Prev
    Next
    INDEX
    Explanations

    picked without replacement

    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
    åıĪä¼ļ
    -0.08
    稿件æĿ¥æºIJ
    -0.08
    æĢİä¹ĪåĬŀåij¢
    -0.08
    illos
    -0.08
    åıĪä¸į
    -0.07
    触è§Ĵ
    -0.07
    illo
    -0.07
    棺æĿIJ
    -0.07
    enhagen
    -0.07
    fine
    -0.07
    POSITIVE LOGITS
    gger
    0.07
    æ³£
    0.07
    çĤ¹åIJį
    0.07
    stract
    0.07
    .ide
    0.07
    Mai
    0.06
    igi
    0.06
    ä¹ĭåīij
    0.06
    è´µ
    0.06
    obi
    0.06
    Activations Density 0.002%

    No Known Activations