© 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. 51044
    Prev
    Next
    INDEX
    Explanations

    squared differences

    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
    aglio
    -0.08
    enhagen
    -0.07
    adni
    -0.07
    è¢«åĽ°
    -0.07
    Aura
    -0.07
     Swamp
    -0.07
    åIJİéĢĢ
    -0.07
    à¸Ńุ
    -0.07
    بÙĪØ·
    -0.07
    fleisch
    -0.07
    POSITIVE LOGITS
    ultan
    0.07
    hip
    0.07
    uger
    0.06
    uml
    0.06
    é¡Ĩ
    0.06
    lacht
    0.06
    ีà¹īยว
    0.06
     powder
    0.06
    arrer
    0.06
    alone
    0.06
    Activations Density 0.003%

    No Known Activations