© 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. 34840
    Prev
    Next
    INDEX
    Explanations

    unknown, instability, loss of control

    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
    ìĸ´ëĤĺ
    -0.07
    serter
    -0.07
    å°½æľī
    -0.07
    ertext
    -0.06
     PROGRAMA
    -0.06
    çīĩçīĩ
    -0.06
     TRAB
    -0.06
    usi
    -0.06
    osomes
    -0.06
    次第
    -0.06
    POSITIVE LOGITS
    带æĿ¥çļĦ
    0.13
    导èĩ´çļĦ
    0.11
    æīĢ带æĿ¥çļĦ
    0.10
    帶ä¾ĨçļĦ
    0.09
    å¼ķåıijçļĦ
    0.09
    ä¼ļ带æĿ¥
    0.09
    éĢłæĪIJçļĦ
    0.08
    带æĿ¥
    0.08
     íĨµíķľ
    0.08
     ìĿ¸íķľ
    0.08
    Activations Density 0.097%

    No Known Activations