© 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. 3775
    Prev
    Next
    INDEX
    Explanations

    plural articles

    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
    ously
    -0.07
    Ùĭ
    -0.07
    ings
    -0.06
    ,
    -0.06
    emon
    -0.06
    less
    -0.06
    gence
    -0.06
    e
    -0.06
    ish
    -0.06
    æ±Łå±±
    -0.06
    POSITIVE LOGITS
     demás
    0.13
    ses
    0.12
    转载请
    0.10
     demais
    0.10
     gì
    0.10
     meisten
    0.10
    pring
    0.10
     mesmos
    0.09
     usual
    0.09
    által
    0.09
    Activations Density 0.009%

    No Known Activations