© 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. 57043
    Prev
    Next
    INDEX
    Explanations

    following punctuation

    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
    uzz
    -0.08
    æĺµ
    -0.07
    erring
    -0.07
    dach
    -0.07
    éĺģä¸ĭ
    -0.07
    ä¸Ģ转
    -0.07
    pur
    -0.07
    akse
    -0.06
    ó
    -0.06
    och
    -0.06
    POSITIVE LOGITS
    ä¼ĺçĤ¹æĺ¯
    0.08
    ä¸ĭåIJĮ
    0.07
    å°ıç»ĵ
    0.07
    _:
    0.07
    èħĨ
    0.07
    è¿Ļ个è§Ĵèī²
    0.06
     اÙĦعÙħ
    0.06
    baran
    0.06
    åİĮ
    0.06
    dojo
    0.06
    Activations Density 0.096%

    No Known Activations