© 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. 60827
    Prev
    Next
    INDEX
    Explanations

    code writing

    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
    loor
    -0.09
    apons
    -0.08
    endcode
    -0.08
    wiss
    -0.08
    ÅĤon
    -0.08
    EGO
    -0.08
     Handy
    -0.08
    bard
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.07
    Descrip
    -0.07
    POSITIVE LOGITS
    éĶĻ误æĪĸ
    0.09
    èĢĮè¨Ģ
    0.08
    èĢĮä¸įæĺ¯
    0.08
     rather
    0.07
     or
    0.07
    çļĦä¸Ģ项
    0.07
    èĢĮéĿŀ
    0.07
     vs
    0.07
    /default
    0.07
     versus
    0.07
    Activations Density 0.011%

    No Known Activations