© 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. 38184
    Prev
    Next
    INDEX
    Explanations

    names, cities, or code definitions

    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
    acea
    -0.08
    à®ļà¯įà®ļ
    -0.08
     депози
    -0.08
    /ext
    -0.08
    irea
    -0.07
    μμ
    -0.07
    à®ŀ
    -0.07
    æĹ¥æĸ°æľĪ
    -0.07
    çľĭåľ¨çľ¼éĩĮ
    -0.07
    moni
    -0.07
    POSITIVE LOGITS
    æľĿ
    0.07
    çķĮ
    0.06
    ufe
    0.06
    EX
    0.06
    éķ
    0.06
     symbolic
    0.06
     worth
    0.06
    okrat
    0.06
    游
    0.06
    ordan
    0.06
    Activations Density 0.826%

    No Known Activations