© 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. 3875
    Prev
    Next
    INDEX
    Explanations

    parameters

    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
    汽车ä¹ĭ家
    -0.08
    SWG
    -0.07
    дÑİ
    -0.07
    åĬ¨åĬ¨
    -0.07
    NotFoundError
    -0.07
    ụy
    -0.07
    _CONV
    -0.07
    strt
    -0.07
    æĵį
    -0.07
    iative
    -0.07
    POSITIVE LOGITS
    åıĤæķ°
    0.11
    åıĤæķ°çļĦ
    0.10
    çļĦåıĤæķ°
    0.10
     parameters
    0.10
    Parameters
    0.09
    parameters
    0.08
     Parameters
    0.08
     parameter
    0.08
    éħįç½®
    0.08
    _parameter
    0.08
    Activations Density 0.082%

    No Known Activations