© 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. 56986
    Prev
    Next
    INDEX
    Explanations

    large numbers or limits

    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
     Mittler
    -0.08
    该å±Ģ
    -0.07
     öz
    -0.07
    ÐļС
    -0.07
    ائÙĦ
    -0.07
    象çīĻ
    -0.07
    -storage
    -0.07
    ÑĦоÑĢа
    -0.07
    æĩĴ
    -0.07
    ertainment
    -0.07
    POSITIVE LOGITS
    erp
    0.09
    utin
    0.07
    teria
    0.07
    enta
    0.07
    å°ĶèĴĻ
    0.06
    pai
    0.06
    ermann
    0.06
    ä¸įåı¯èĥ½çļĦ
    0.06
    è¹
    0.06
    jing
    0.06
    Activations Density 0.008%

    No Known Activations