© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46757
    Prev
    Next
    INDEX
    Explanations

    such as

    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
     fanta
    -0.08
    è·¯åĮĹ
    -0.08
    áĥļáĥĶ
    -0.08
    cÃŃ
    -0.08
    ÙĨدÛĮ
    -0.08
    orny
    -0.08
    esty
    -0.08
    ëĿ¼ìĿ´
    -0.08
    ัส
    -0.08
    çīĪæĿĥå½Ĵ
    -0.08
    POSITIVE LOGITS
    :
    0.09
    ä¾ĭå¦Ĥ
    0.08
    诸å¦Ĥ
    0.08
    ,
    0.08
     beispielsweise
    0.08
     ones
    0.08
     notamment
    0.07
     halnya
    0.07
    nam
    0.07
     napÅĻÃŃklad
    0.07
    Activations Density 0.535%

    No Known Activations