© 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. 57540
    Prev
    Next
    INDEX
    Explanations

    variant, talk, tough, Disney, Guy

    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
    afone
    -0.09
    å·ĿåĮº
    -0.08
    è´¯
    -0.08
    italia
    -0.07
     beze
    -0.07
    æľŃ
    -0.07
     Rasul
    -0.07
    rast
    -0.07
    ials
    -0.07
    psc
    -0.07
    POSITIVE LOGITS
     likewise
    0.10
    åIJĮä¸Ĭ
    0.10
     similarly
    0.08
    åIJĮæł·
    0.08
    åIJĮæł·çļĦ
    0.08
    åIJĮæł·æĺ¯
    0.08
    åIJĮ樣
    0.08
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.08
    Similarly
    0.08
     same
    0.07
    Activations Density 0.106%

    No Known Activations