© 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. 37505
    Prev
    Next
    INDEX
    Explanations

    .setScene, .appendChild, .Role

    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
    uno
    -0.08
    æĺ¯åħ¨
    -0.07
    rock
    -0.07
    osa
    -0.07
    浦
    -0.07
    মন
    -0.07
    urf
    -0.07
    âĤ¬,
    -0.07
    pb
    -0.06
     à¹Ģà¸Ļืà¹Īà¸Ńà¸ĩ
    -0.06
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.14
    对æѤ
    0.11
    æį®æѤ
    0.11
     accordingly
    0.11
    å°įæѤ
    0.10
    åĪ°è¿Ļ个
    0.10
    以æŃ¤ä¸º
    0.10
    åľ¨è¿ĻäºĽ
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    ä¸İæѤ
    0.10
    Activations Density 0.003%

    No Known Activations