© 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. 25135
    Prev
    Next
    INDEX
    Explanations

    Cambridge Analytica

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Gelt
    -0.06
    athi
    -0.06
    orer
    -0.06
    å²ģçļĦåŃ©åŃIJ
    -0.06
     scatter
    -0.06
    æŁ¥çľĭ
    -0.06
     pronost
    -0.06
    ç©¿éĢı
    -0.06
     ith
    -0.06
    è·Ľ
    -0.06
    POSITIVE LOGITS
    Subset
    0.09
     bizar
    0.09
    wich
    0.08
     colum
    0.08
    åĬŀ主任
    0.08
    ambah
    0.08
    类似éĹ®é¢ĺ
    0.07
    æĻĤåł±
    0.07
    XY
    0.07
    zilla
    0.07
    Activations Density 0.009%

    No Known Activations