© 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. 21416
    Prev
    Next
    INDEX
    Explanations

    store/save

    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
    ton
    -0.07
    _OPT
    -0.07
    æĿ
    -0.07
    åķ§
    -0.06
    allet
    -0.06
    odies
    -0.06
    _msgs
    -0.06
    urie
    -0.06
    飵
    -0.06
    .production
    -0.06
    POSITIVE LOGITS
    à¹Ħวà¹īà¹ĥà¸Ļ
    0.10
    缸åºĶ
    0.08
    Into
    0.08
    æĺ¥æļĸ
    0.08
     vÃło
    0.08
    åĪ°èĩªå·±çļĦ
    0.08
    缸åºĶçļĦ
    0.08
    ลà¸ĩà¹ĥà¸Ļ
    0.07
    缸æĩī
    0.07
     TENT
    0.07
    Activations Density 0.045%

    No Known Activations