© 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. 34785
    Prev
    Next
    INDEX
    Explanations

    country names and people

    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
    è´Łæĭħ
    -0.08
    Äįov
    -0.07
    ä¸ĢçĤ¹åĦ¿
    -0.07
    éĢģèĩ³
    -0.07
    æĹħç¨ĭ
    -0.07
    veda
    -0.07
     Raider
    -0.07
    éen
    -0.07
    ienes
    -0.07
    occhi
    -0.07
    POSITIVE LOGITS
    ä¸Ĭåĵģ
    0.07
    港åĮº
    0.07
    pos
    0.06
    rasil
    0.06
    igator
    0.06
    ÙĪØ·
    0.06
     اÛĮ
    0.06
    åĤ»åĤ»
    0.06
     scare
    0.06
    èįĨ
    0.06
    Activations Density 0.036%

    No Known Activations