© 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. 57310
    Prev
    Next
    INDEX
    Explanations

    essay, research paper, forums, franchise, Adamson, chromatography, May

    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
    bard
    -0.08
    grave
    -0.07
    à¸Ńรà¹Įà¸ģ
    -0.07
    arzy
    -0.07
    à¸ģะ
    -0.07
    éron
    -0.07
    kers
    -0.07
     komplette
    -0.06
    .sparse
    -0.06
    çİĩåľ¨
    -0.06
    POSITIVE LOGITS
    Å¡t
    0.07
    æŃ»ä¸į
    0.07
    ä¸ĢèĤ¡
    0.07
    es
    0.07
    اد
    0.07
    Å¡in
    0.06
    {}
    0.06
    é£ĵé£İ
    0.06
    اض
    0.06
    ósito
    0.06
    Activations Density 0.006%

    No Known Activations