© 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. 18329
    Prev
    Next
    INDEX
    Explanations

    template syntax and type 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
    Ã¤ÃŁ
    -0.07
    åįķä¸Ģ
    -0.06
    lj
    -0.06
    áĢŀáĢ¬
    -0.06
    åįķä¸ĢçļĦ
    -0.06
    æ¡ĤåĽŃ
    -0.06
    ķĮ
    -0.06
    single
    -0.06
     single
    -0.06
    ULA
    -0.06
    POSITIVE LOGITS
    èĿ
    0.09
    è¨ĢãģĨ
    0.08
    obl
    0.07
    दार
    0.07
    rab
    0.07
    ç®ķ
    0.07
    ÐijÐł
    0.07
    agens
    0.07
    å±ĬæŶ
    0.07
    agem
    0.07
    Activations Density 0.007%

    No Known Activations