© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7174
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    Negative Logits
    θÏħ
    -0.07
    çħ§çĿĢ
    -0.06
    айд
    -0.06
    ãĥ¡ãĤ¤
    -0.06
    fyl
    -0.06
    ijd
    -0.06
    elivery
    -0.06
    ewolf
    -0.06
    _INCLUDED
    -0.06
    _semaphore
    -0.06
    POSITIVE LOGITS
    ä¹IJçļĦ
    0.08
    温馨æıIJéĨĴ
    0.07
     articul
    0.07
    ç®Ģ书
    0.07
    ļĮ
    0.07
    dür
    0.07
    æ§Ľ
    0.07
    ancia
    0.06
    ember
    0.06
    bpp
    0.06
    Activations Density 0.030%

    No Known Activations