© 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. 34848
    Prev
    Next
    INDEX
    Explanations

    locations (north, Liberty, ML)

    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
    对åİŁåijĬ
    -0.08
    oyer
    -0.08
    éĢĨåIJij
    -0.07
     everytime
    -0.07
    éĢĨåıĺ
    -0.07
    éĢĨ
    -0.07
    hani
    -0.07
     Thá»ĭ
    -0.07
    对åħļ
    -0.07
    wij
    -0.07
    POSITIVE LOGITS
    okka
    0.07
    ানà§įত
    0.07
    .uk
    0.07
    æıIJ
    0.06
    olan
    0.06
    uo
    0.06
     exagger
    0.06
     scn
    0.06
    LLL
    0.06
     Sunny
    0.06
    Activations Density 0.001%

    No Known Activations