© 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. 20844
    Prev
    Next
    INDEX
    Explanations

    geographic locations and units

    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
    åľ¨åħ¨çľģ
    -0.07
    ehl
    -0.07
    ÙĪجب
    -0.07
    女è£ħ
    -0.07
    ahari
    -0.07
    icut
    -0.07
    igente
    -0.07
    å°ıäºĮ
    -0.07
    stal
    -0.07
    è·¯éĢı
    -0.07
    POSITIVE LOGITS
    çļĦä¼Łå¤§
    0.06
    å¡ŀ
    0.06
    å®ĩå®Ļ
    0.06
    зин
    0.06
    FieldValue
    0.06
    éĻ¨çŁ³
    0.06
    æģIJ
    0.06
    astr
    0.06
    çĢļ
    0.06
    æĸĭ
    0.06
    Activations Density 0.002%

    No Known Activations