© 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. 45142
    Prev
    Next
    INDEX
    Explanations

    percentages, distances, and quantities

    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
    çĸı
    -0.07
     Schul
    -0.06
    ç¨ĭ度
    -0.06
    书é¦Ļ
    -0.06
     Bened
    -0.06
    epro
    -0.06
    efeld
    -0.06
    Pro
    -0.06
    èĿ
    -0.06
    太空
    -0.06
    POSITIVE LOGITS
    inn
    0.08
     Spears
    0.08
    deaux
    0.07
    åŁł
    0.07
    adis
    0.07
    serter
    0.07
     coz
    0.07
    èµ°ä¸ĭåİ»
    0.07
    cea
    0.07
    icot
    0.07
    Activations Density 0.039%

    No Known Activations