© 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. 16823
    Prev
    Next
    INDEX
    Explanations

    principal end

    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
    éĵ¿
    -0.08
    æĪĸä¸į
    -0.07
    _VERBOSE
    -0.07
    зÑĢа
    -0.07
    ëł´
    -0.06
    нÑĮÑı
    -0.06
    å®ļåIJij
    -0.06
    æŀ¸
    -0.06
    swire
    -0.06
    ìa
    -0.06
    POSITIVE LOGITS
    åĴĮåIJİ
    0.09
    odle
    0.08
    åĴĮæĬķèµĦ
    0.07
    ãģ«å½±éŁ¿
    0.07
    ehlen
    0.07
     ÙĦØ°
    0.07
    dish
    0.07
    en
    0.07
    åĴĮäºĮ
    0.07
    gau
    0.07
    Activations Density 0.011%

    No Known Activations