© 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. 4659
    Prev
    Next
    INDEX
    Explanations

    card, Illinois, commissions, Historical, subject, city

    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
    ationToken
    -0.09
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    NotificationCenter
    -0.08
    cade
    -0.07
    DataExchange
    -0.07
    ihad
    -0.07
    alus
    -0.07
    BitFields
    -0.07
    actionDate
    -0.07
    afil
    -0.07
    POSITIVE LOGITS
    åı·
    0.06
    第äºĮç§į
    0.06
     Dw
    0.06
    åħ³
    0.06
    æŶä¸ĭ
    0.06
    ãĤ®ãĥ¥
    0.06
    èİ«
    0.06
    箫
    0.06
    ä½łåĪ«
    0.06
    amic
    0.06
    Activations Density 0.016%

    No Known Activations