© 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. 63882
    Prev
    Next
    INDEX
    Explanations

    anti / ant / nourish / relax

    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
    ä¸įåı¯æĢķ
    -0.08
    ardini
    -0.07
    ussin
    -0.07
    çĭŀ
    -0.07
    æĭħå¿ĥçļĦ
    -0.07
    azzi
    -0.07
     Chun
    -0.07
    ربÙĬ
    -0.07
    vier
    -0.07
    reated
    -0.07
    POSITIVE LOGITS
    åĴĮæıIJé«ĺ
    0.08
    åĴĮæıIJåįĩ
    0.08
    èĶ»
    0.08
    ordes
    0.07
    æ¢ĵ
    0.07
    åĴĮæĶ¹åĸĦ
    0.07
    çĿ£
    0.07
    åĭĿæīĭ
    0.07
    esm
    0.07
    eryl
    0.07
    Activations Density 0.001%

    No Known Activations