© 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. 15067
    Prev
    Next
    INDEX
    Explanations

    programming language keywords or syntax

    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
    丽åįİ
    -0.07
    åĮºåĮº
    -0.07
    飵
    -0.07
    eph
    -0.07
    jos
    -0.06
    uc
    -0.06
    imi
    -0.06
    jpg
    -0.06
    说起æĿ¥
    -0.06
    imp
    -0.06
    POSITIVE LOGITS
    uell
    0.08
    å¾·éĩĮ
    0.08
    èĪįå¾Ĺ
    0.07
    à¹Ħล
    0.07
    aczy
    0.07
    amped
    0.07
    ä¸ĢæĻĤ
    0.07
    ListOf
    0.07
    Globals
    0.07
    odu
    0.07
    Activations Density 0.001%

    No Known Activations