© 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. 45620
    Prev
    Next
    INDEX
    Explanations

    | * \ + ł

    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
    ungi
    -0.08
    模
    -0.07
     dime
    -0.07
    ÐłÐ¢
    -0.07
    راÙħ
    -0.07
    ɵ
    -0.07
    ุà¸ĩ
    -0.07
    spell
    -0.07
    signed
    -0.07
    lers
    -0.07
    POSITIVE LOGITS
     sort
    0.07
    åĴĮæĿ¨
    0.06
     Karls
    0.06
    ward
    0.06
    åĬ¨åĬĽåѦ
    0.06
    ÑĪеÑĤ
    0.06
    å¸ĺ
    0.06
    uisse
    0.06
    ìn
    0.06
    [unit
    0.06
    Activations Density 0.016%

    No Known Activations