© 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. 44488
    Prev
    Next
    INDEX
    Explanations

    US states

    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
    (er
    -0.08
     Galler
    -0.07
    对åħļ
    -0.07
    ç©¿è¡Į
    -0.07
    èĬĿåĬł
    -0.07
    è¿Ľåİ»äºĨ
    -0.07
    adÃŃ
    -0.07
    apor
    -0.07
    æĹłè¯¯
    -0.07
    åĩ¿
    -0.07
    POSITIVE LOGITS
    éĵĥ
    0.07
    é£
    0.06
    ege
    0.06
    åĬį
    0.06
    oracle
    0.06
    ocities
    0.06
    éĪ´
    0.06
    оÑĢо
    0.06
    çļĦåīij
    0.06
    ETF
    0.06
    Activations Density 0.272%

    No Known Activations