© 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. 23762
    Prev
    Next
    INDEX
    Explanations

    difference

    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
    Sortable
    -0.07
    å°ıæľī
    -0.07
     recipro
    -0.07
    丹
    -0.07
    _PARAMETERS
    -0.07
    åŁ¹èĤ²åĴĮ
    -0.07
    äºļ
    -0.06
     Schönh
    -0.06
    inn
    -0.06
    è¯ł
    -0.06
    POSITIVE LOGITS
    difference
    0.12
    å·®é¢Ŀ
    0.11
     difference
    0.10
    Difference
    0.10
     Difference
    0.09
    å·®
    0.09
     diferença
    0.09
     ÑĢазниÑĨа
    0.09
    _difference
    0.09
    subtract
    0.08
    Activations Density 0.070%

    No Known Activations