© 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. 22655
    Prev
    Next
    INDEX
    Explanations

    numbers followed by categories

    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
    kens
    -0.08
    watan
    -0.07
    æĬĬ好
    -0.07
    мона
    -0.06
    ļľ
    -0.06
    uccio
    -0.06
     СÑİ
    -0.06
    emd
    -0.06
    ember
    -0.06
    velt
    -0.06
    POSITIVE LOGITS
     sonstige
    0.09
    çļĦåħ¶ä»ĸ
    0.09
     others
    0.08
    åħ¶ä»ĸ
    0.08
    (er
    0.08
    åħ¶å®ĥçļĦ
    0.08
    åħ¶å®ĥ
    0.08
    надÑĨаÑĤÑĮ
    0.08
     diantaranya
    0.08
    ä¸İä¹ĭ
    0.08
    Activations Density 0.176%

    No Known Activations