© 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. 39648
    Prev
    Next
    INDEX
    Explanations

    numbers and words

    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
    è¿ĿèĢħ
    -0.07
    çļĦ人ä¼ļ
    -0.07
    æ¸Ĺ
    -0.07
    Sent
    -0.06
    ãģ¼
    -0.06
    ä»ģçĪ±
    -0.06
    imed
    -0.06
    iced
    -0.06
    ÙĪاÙĦ
    -0.06
    ions
    -0.06
    POSITIVE LOGITS
    æ³ķåŃIJ
    0.08
    emachine
    0.08
    FER
    0.08
    erton
    0.08
    èĬ³
    0.08
    ائÙĬ
    0.08
    okok
    0.07
    алан
    0.07
    ä¸įåºĶæ±Ĥ
    0.07
    atoon
    0.07
    Activations Density 0.049%

    No Known Activations