© 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. 2970
    Prev
    Next
    INDEX
    Explanations

    mathematical function arguments

    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
    apun
    -0.08
    igent
    -0.07
    odus
    -0.07
     CR
    -0.07
    ancing
    -0.07
    ommer
    -0.07
    =default
    -0.07
    å©Ĩ
    -0.07
     Craig
    -0.07
    :hidden
    -0.07
    POSITIVE LOGITS
    spo
    0.07
    ÙĭÙijا
    0.07
    å¿ĥä¸Ĭ
    0.06
    venta
    0.06
    лежа
    0.06
    è«ĭåķı
    0.06
    ('.'
    0.06
    æĭľæīĺ
    0.06
    çĹħæĥħæııè¿°
    0.06
    æ´»å¾Ĺ
    0.06
    Activations Density 0.123%

    No Known Activations