© 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. 51307
    Prev
    Next
    INDEX
    Explanations

    variable names and code elements

    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
    æĿ¿å¼ı
    -0.08
    aisen
    -0.07
    ASSERT
    -0.07
    ich
    -0.07
    ISOString
    -0.07
    åŁºä¸ļ
    -0.07
     abord
    -0.07
     Arr
    -0.07
    ([&
    -0.07
    éĤ¸
    -0.07
    POSITIVE LOGITS
    åĵİ
    0.07
    Prog
    0.07
    nez
    0.07
    trand
    0.07
     Doe
    0.07
    Dam
    0.07
    oitu
    0.07
    wane
    0.07
    çĴĢ
    0.06
    dam
    0.06
    Activations Density 0.017%

    No Known Activations