© 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. 55203
    Prev
    Next
    INDEX
    Explanations

    are [adjective]

    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
    ä¸įè°ĥ
    -0.09
    uro
    -0.08
    ardo
    -0.08
    çĭ¬ç«ĭ
    -0.08
    ëŁ¼
    -0.08
    conv
    -0.07
    è¶³å¤Ł
    -0.07
    áĥIJáĥłáĥĹ
    -0.07
     Independence
    -0.07
    çį¨ç«ĭ
    -0.07
    POSITIVE LOGITS
     sih
    0.07
    erima
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    haled
    0.06
    å·²å°Ĩ
    0.06
    æĬĬä¸Ģ个
    0.06
    inol
    0.06
    **|
    0.06
    娥
    0.06
     Mahmoud
    0.06
    Activations Density 0.001%

    No Known Activations