© 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. 16027
    Prev
    Next
    INDEX
    Explanations

    code or identifier snippets

    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
    ftime
    -0.08
    ibl
    -0.08
    dba
    -0.08
    agni
    -0.08
    æľīæķĪçİĩ
    -0.08
    xfd
    -0.07
    æĢ»éĩıçļĦ
    -0.07
    arendra
    -0.07
    ITT
    -0.07
    æ¾İ
    -0.07
    POSITIVE LOGITS
    åĴĮ第
    0.09
    åı·æĸĩ件
    0.08
    åı·
    0.08
    èĻŁ
    0.08
     onwards
    0.07
    åı·åĴĮ
    0.07
     onward
    0.07
    åı·çļĦ
    0.07
    ë²Ī
    0.07
    éĽį
    0.07
    Activations Density 0.240%

    No Known Activations