© 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. 20083
    Prev
    Next
    INDEX
    Explanations

    color definitions and styles

    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
    วà¸Ķ
    -0.07
     inc
    -0.07
    åıĮéĿ¢
    -0.07
    æĬĺä¸įæī£
    -0.07
     Herc
    -0.07
    utt
    -0.07
    еÑģÑĤво
    -0.07
    ìĩł
    -0.07
    tons
    -0.06
    便
    -0.06
    POSITIVE LOGITS
    饱åĴĮ度
    0.08
    inactive
    0.07
    oded
    0.07
    æĿ¥ä¹ĭ
    0.07
    _binding
    0.07
    uccio
    0.06
     ineffective
    0.06
    æĸĩåĵ²
    0.06
    okra
    0.06
     inactive
    0.06
    Activations Density 0.049%

    No Known Activations