© 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. 551
    Prev
    Next
    INDEX
    Explanations

    probability of picking sequences

    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
    ampa
    -0.08
    å¾ĹæĿ¥
    -0.06
    lining
    -0.06
    æīĢåģļçļĦ
    -0.06
    æĹłæķ°æ¬¡
    -0.06
    eton
    -0.06
    åĩłåįģå¹´
    -0.06
    ä¸įåıĬ
    -0.06
     dirt
    -0.06
    ìĪľ
    -0.06
    POSITIVE LOGITS
    å¦ĤæŃĮ
    0.08
    足çļĦ
    0.08
    teenth
    0.07
    leter
    0.07
    éĽĨä¸Ńäºİ
    0.07
    íĥķ
    0.07
    ä¸Ģä½ĵçļĦ
    0.07
    à¸ļ
    0.07
    entif
    0.07
    braco
    0.07
    Activations Density 0.032%

    No Known Activations