© 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. 41541
    Prev
    Next
    INDEX
    Explanations

    special numeric values and missing data

    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
    iew
    -0.07
    chy
    -0.07
    æ´ĭ溢
    -0.07
     complémentaire
    -0.06
    衣裳
    -0.06
    ÑģÑĤÑĢой
    -0.06
    æ²īçĿĢ
    -0.06
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.06
    裳
    -0.06
    arily
    -0.06
    POSITIVE LOGITS
    estin
    0.09
    pons
    0.07
     تÙĤرÙĬب
    0.07
    nown
    0.07
     جداÙĭ
    0.07
     Peb
    0.07
    enj
    0.07
    prus
    0.07
    دا
    0.07
    ↵                        ↵
    0.07
    Activations Density 0.003%

    No Known Activations