© 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. 37612
    Prev
    Next
    INDEX
    Explanations

    geometric mean

    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
    祺
    -0.07
    æīĵåĵį
    -0.07
    ç§ij夫
    -0.07
    å¨ģé£İ
    -0.07
    å¨ģæѦ
    -0.07
    upil
    -0.07
    ç£ģæĢ§
    -0.07
    å¿ĹåĪļ
    -0.06
    аÑĩ
    -0.06
    รà¸Ńà¸Ķ
    -0.06
    POSITIVE LOGITS
     optimization
    0.08
     Optimization
    0.08
    çĶŁäº§
    0.08
    Optimizer
    0.08
    best
    0.07
    éĢłåĮĸ
    0.07
    optim
    0.07
    åľ¨çĶŁäº§
    0.07
     optim
    0.07
    .Setup
    0.07
    Activations Density 0.014%

    No Known Activations