© 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. 34905
    Prev
    Next
    INDEX
    Explanations

    removes/recreates/relegated

    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
    berger
    -0.08
    é¢ĦéĢī
    -0.07
     pe
    -0.07
    ä¸įæŶ
    -0.07
    gue
    -0.07
    æĻĤãĢħ
    -0.06
    ener
    -0.06
    führung
    -0.06
    chet
    -0.06
    orda
    -0.06
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.10
    éļıåį³
    0.09
     instantly
    0.09
    Immediately
    0.09
     немед
    0.08
     immediately
    0.08
    ä¼´éļıçĿĢ
    0.08
     Immediately
    0.08
    upal
    0.08
    ç«ĭåĪ»
    0.08
    Activations Density 0.009%

    No Known Activations