© 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. 13307
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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
    ermen
    -0.08
    edb
    -0.08
    bib
    -0.07
     Wilkinson
    -0.07
    并æĬ¥
    -0.07
    /../
    -0.07
    并æĬĬ
    -0.07
    Ïģικ
    -0.07
    .twig
    -0.07
    ientos
    -0.07
    POSITIVE LOGITS
    ÏĤ
    0.08
    estre
    0.08
    odu
    0.08
    ush
    0.07
    æĪijåĴĮæĪijçļĦ
    0.07
    LTR
    0.07
    quilla
    0.06
    éħ·
    0.06
    нÑı
    0.06
    olim
    0.06
    Activations Density 0.006%

    No Known Activations