© 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. 52138
    Prev
    Next
    INDEX
    Explanations

    place names and technical terms

    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
     herself
    -0.10
     stessa
    -0.07
    engan
    -0.07
    jej
    -0.07
    łí
    -0.07
     Akademie
    -0.07
     हà¥ĭतà¥Ģ
    -0.07
    ouverte
    -0.07
    égi
    -0.07
    adows
    -0.07
    POSITIVE LOGITS
     koji
    0.07
     quieter
    0.07
     religieux
    0.07
    quiet
    0.07
    onian
    0.07
    å¼
    0.07
    åĿĤ
    0.06
     коÑĺи
    0.06
     côt
    0.06
     który
    0.06
    Activations Density 0.004%

    No Known Activations