© 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. 591
    Prev
    Next
    INDEX
    Explanations

    measures to improve education

    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
    ãĥĬãĥ³
    -0.07
     intros
    -0.07
    å¿ĥåĬ¨
    -0.07
    åĪĺæĸĩ
    -0.06
    adal
    -0.06
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.06
    å¼łå»º
    -0.06
    åĨħåIJij
    -0.06
    aszt
    -0.06
    anza
    -0.06
    POSITIVE LOGITS
    èŁ¹
    0.08
    âĢ¦âĢ¦ãĢĤ
    0.08
    à¸ī
    0.08
     [âĢ¦
    0.07
    CUS
    0.07
    issen
    0.07
    èĤ´
    0.07
    teur
    0.07
    soever
    0.07
    esus
    0.07
    Activations Density 0.290%

    No Known Activations