© 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. 37530
    Prev
    Next
    INDEX
    Explanations

    sudden changes

    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
    纵横
    -0.07
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.07
    å°ijä¸įäºĨ
    -0.07
    åľ¨ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.07
    гина
    -0.07
    åĬ¨è¾Ħ
    -0.06
    çĮ¬
    -0.06
    å·¢
    -0.06
     pairwise
    -0.06
    离ä¸įå¼Ģ
    -0.06
    POSITIVE LOGITS
     instantly
    0.17
     suddenly
    0.17
    çŀ¬éĹ´
    0.16
     instant
    0.16
     sudden
    0.15
     abruptly
    0.14
     мгновен
    0.14
    çªģçĦ¶
    0.14
    instant
    0.14
    Instant
    0.13
    Activations Density 0.097%

    No Known Activations