© 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. 19763
    Prev
    Next
    INDEX
    Explanations

    research purpose or context

    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
    erdale
    -0.07
     mysterious
    -0.07
    ä»ĸ家
    -0.07
    volgens
    -0.07
    åĩºåIJįçļĦ
    -0.07
    éªĹåıĸ
    -0.07
     caden
    -0.07
    Ł
    -0.07
    esda
    -0.07
    éķ¿å¾Ĺ
    -0.07
    POSITIVE LOGITS
     herein
    0.10
    research
    0.08
    æĹ¨åľ¨
    0.08
    æľ¬çłĶ究
    0.08
     focus
    0.08
     outcomes
    0.08
     methodologies
    0.08
     research
    0.08
     conceptual
    0.07
    çļĦçłĶ究
    0.07
    Activations Density 0.509%

    No Known Activations