© 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. 62519
    Prev
    Next
    INDEX
    Explanations

    Doppler effect

    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
    æ³Ľ
    -0.08
    flip
    -0.07
    ÑħозÑıй
    -0.07
    å¾Īå¤ļ家éķ¿
    -0.07
    igin
    -0.07
    ç¼®
    -0.07
    åıijæĮ¥
    -0.06
    æī¹
    -0.06
     skim
    -0.06
    озÑıй
    -0.06
    POSITIVE LOGITS
     stationary
    0.08
    .effects
    0.07
     perc
    0.07
    -Trump
    0.07
    主åĬ¨
    0.07
    åķ¼
    0.07
    distance
    0.07
    å¢ŀåİĭ
    0.07
    imity
    0.07
     Dop
    0.07
    Activations Density 0.002%

    No Known Activations