© 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. 61514
    Prev
    Next
    INDEX
    Explanations

    sentence start after nbsp

    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
     Nope
    -0.08
    eload
    -0.08
    ProcAddress
    -0.07
    paramref
    -0.07
    گز
    -0.07
    æijĦ
    -0.07
    semblies
    -0.07
    umis
    -0.07
    erop
    -0.07
     irresist
    -0.06
    POSITIVE LOGITS
    inti
    0.09
    å¤ļ好
    0.08
    æľīéģĵ
    0.08
    irim
    0.07
    uto
    0.07
    丹丹
    0.07
    ichen
    0.06
    ä¸įåIJĮçļĦæĺ¯
    0.06
    rina
    0.06
    ven
    0.06
    Activations Density 0.144%

    No Known Activations