© 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. 44326
    Prev
    Next
    INDEX
    Explanations

    determine whether

    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
    åı¯æ¢¦
    -0.08
    enges
    -0.08
    æĪijæĿ¥è¯´
    -0.08
    aju
    -0.08
    请ä¸İ
    -0.08
    æľ¬ç«ĻåĨħ容
    -0.08
    ooth
    -0.08
    aterna
    -0.08
    uder
    -0.07
    åı¯æĥ³
    -0.07
    POSITIVE LOGITS
    ies
    0.07
     whether
    0.06
    edar
    0.06
    彤
    0.06
    mark
    0.06
    æĺ¯ä¸įæĺ¯
    0.06
    åĪĨæŀIJ
    0.06
    ä¸ŀ
    0.06
     [âĢ¦]
    0.05
    以为çĦ¶
    0.05
    Activations Density 0.001%

    No Known Activations