© 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. 8906
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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
    ÑĢÑĥз
    -0.08
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.08
    pios
    -0.08
    timb
    -0.08
    stime
    -0.08
    æĹłæĦ§
    -0.07
    Ø·ÙĤ
    -0.07
    memberOf
    -0.07
    plevel
    -0.07
    ढ़
    -0.07
    POSITIVE LOGITS
    orary
    0.07
    大éĢļ
    0.06
    åĿŀ
    0.06
    tings
    0.06
    æīĵåĩº
    0.06
    缸åºĶçļĦ
    0.06
    æŁĵæĸĻ
    0.06
    ó
    0.06
    ÃŃ
    0.06
     Push
    0.06
    Activations Density 0.007%

    No Known Activations