© 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. 46603
    Prev
    Next
    INDEX
    Explanations

    options and preferences

    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
    ãģ¤ãģ¶
    -0.08
    vár
    -0.08
    起泡
    -0.08
    /umd
    -0.08
    æłĩè¯Ĩçłģ
    -0.08
    çIJ¼
    -0.07
    produ
    -0.07
    ymar
    -0.07
    åıįåºĶè¿ĩæĿ¥
    -0.07
    nbr
    -0.07
    POSITIVE LOGITS
     tweaks
    0.10
     tweaking
    0.09
     settings
    0.09
     adjustments
    0.09
    Settings
    0.09
     tweak
    0.08
    æĽ´æĶ¹
    0.08
     ajustes
    0.08
     Settings
    0.08
    è°ĥæķ´
    0.07
    Activations Density 0.197%

    No Known Activations