© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63091
    Prev
    Next
    INDEX
    Explanations

    normalized, scaled, units

    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
    ва
    -0.08
    è£
    -0.07
    empla
    -0.07
    CIAS
    -0.07
    æĹĹé¼ĵ
    -0.07
    nage
    -0.07
    å·¢
    -0.07
    hin
    -0.07
    ROWS
    -0.06
    èľ»
    -0.06
    POSITIVE LOGITS
     normalized
    0.09
    åħĭåĬĽ
    0.09
     scaled
    0.09
    scaled
    0.09
    åįķä½į为
    0.09
    åįķä½į
    0.08
    å¿ĺ
    0.08
     units
    0.08
    normalized
    0.08
     unitÃł
    0.08
    Activations Density 0.088%

    No Known Activations