© 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. 49002
    Prev
    Next
    INDEX
    Explanations

    consider the following

    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
    ipe
    -0.08
    ick
    -0.08
    è¿Ļç§įä¸ľè¥¿
    -0.07
    ç¥ŀçİĭ
    -0.07
    aver
    -0.07
    æŁIJç§į
    -0.07
    ibre
    -0.07
     whatever
    -0.07
    ekyll
    -0.07
    ä»Ģä¹Īæł·çļĦ
    -0.07
    POSITIVE LOGITS
     besides
    0.07
    ز
    0.07
    ãĢĤ
    0.07
    å¾ĹçŁ¥
    0.07
    .
    0.07
     lagi
    0.06
    elius
    0.06
    :
    0.06
    heen
    0.06
    ر
    0.06
    Activations Density 0.002%

    No Known Activations