© 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. 44261
    Prev
    Next
    INDEX
    Explanations

    proper subspaces

    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
    atem
    -0.08
    å°ĨæĿ¥çļĦ
    -0.07
    /rc
    -0.07
    æį¶
    -0.07
    obj
    -0.07
    æ¹ĥ
    -0.07
    %c
    -0.06
    à¹Īาà¸Ļ
    -0.06
    unga
    -0.06
    ìĿµ
    -0.06
    POSITIVE LOGITS
    yser
    0.09
     randomly
    0.08
     subgroup
    0.08
    éļıæľº
    0.08
     subset
    0.07
    equip
    0.07
     Walsh
    0.07
    quip
    0.07
    éģįåİĨ
    0.07
    inion
    0.07
    Activations Density 0.003%

    No Known Activations