© 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. 19008
    Prev
    Next
    INDEX
    Explanations

    plastic, resin, polymer

    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
    ocz
    -0.08
     inox
    -0.07
    ä¸įéĶĪéĴ¢
    -0.07
     Inox
    -0.07
    ostro
    -0.07
    éĵģçŁ¿çŁ³
    -0.07
     ref
    -0.07
    èĬľ
    -0.07
     ores
    -0.06
     Sass
    -0.06
    POSITIVE LOGITS
    soft
    0.10
    软
    0.10
    软çļĦ
    0.10
     soft
    0.09
     softer
    0.09
    æŁĶ软
    0.09
    æŁĶå¼±
    0.09
    æŁĶæĢ§
    0.09
    æŁĶ软çļĦ
    0.09
    è»Ł
    0.09
    Activations Density 0.114%

    No Known Activations