© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33939
    Prev
    Next
    INDEX
    Explanations

    structure, material, or component

    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
    å·´åħĭ
    -0.07
    åĴĮä¸į
    -0.07
    ä¸įå½±åĵį
    -0.07
    åĴĮåŁºæľ¬
    -0.06
    ä¸įåħ¥
    -0.06
    etek
    -0.06
     overe
    -0.06
    θο
    -0.06
    æĪIJ为äºĨ
    -0.06
    اÙģÙĬØ©
    -0.06
    POSITIVE LOGITS
    å¼ıçļĦ
    0.08
    -wide
    0.08
    -style
    0.07
    halle
    0.07
    etsy
    0.07
    å¼ı
    0.07
    ä½ĵçļĦ
    0.07
    èĢ
    0.07
    æľ¬èº«
    0.07
    人çľĭè¿ĩ
    0.07
    Activations Density 0.170%

    No Known Activations