© 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. 23256
    Prev
    Next
    INDEX
    Explanations

    ending words like "-ly"

    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
    çļĦè¿Ļä¸Ģ
    -0.08
    åѦèĢĮ
    -0.07
    **”
    -0.07
    *
    -0.07
    >(),
    -0.07
    ...',
    -0.07
    **),
    -0.07
    è¿Ļæł·ä¸Ģç§į
    -0.07
    -
    -0.07
    ä¹ĭäºİ
    -0.07
    POSITIVE LOGITS
    che
    0.09
    áŁĶ
    0.07
    éĻĪå¿Ĺ
    0.07
    cky
    0.07
    ksz
    0.07
    landen
    0.07
    пÑıÑĤ
    0.07
    cpy
    0.07
    å°±æīĵ
    0.07
    jsc
    0.07
    Activations Density 0.002%

    No Known Activations