© 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. 41930
    Prev
    Next
    INDEX
    Explanations

    schema keywords

    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
    ä¸įåı¯æĢķ
    -0.08
    er
    -0.08
    eca
    -0.08
    mét
    -0.07
    åIJĮæ¯Ķä¸Ĭåįĩ
    -0.07
    erma
    -0.07
    erot
    -0.07
    INGTON
    -0.07
    à§ģষ
    -0.07
     slan
    -0.07
    POSITIVE LOGITS
    ç¹ģ
    0.07
     Deal
    0.07
    itik
    0.06
    æĥ³ä½ł
    0.06
    опеÑĢа
    0.06
    gate
    0.06
    apel
    0.06
    YYY
    0.06
    (Container
    0.06
     favorites
    0.06
    Activations Density 0.001%

    No Known Activations