© 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. 34877
    Prev
    Next
    INDEX
    Explanations

    country codes and names

    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
    ecu
    -0.08
    มà¸Ļ
    -0.08
    annon
    -0.07
     Brasileiro
    -0.07
    天河
    -0.07
    ÑĨова
    -0.07
    ä¸įè¿ĺ
    -0.07
    æ±Ģ
    -0.07
    åĴĮæľī
    -0.07
    uttle
    -0.07
    POSITIVE LOGITS
    åĵī
    0.07
    ässer
    0.06
    éĹª
    0.06
    大åħ¬
    0.06
    ologies
    0.06
    .flash
    0.06
    unan
    0.06
    å°±æĢķ
    0.06
    unts
    0.06
    æ´¾
    0.06
    Activations Density 0.518%

    No Known Activations