© 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. 4896
    Prev
    Next
    INDEX
    Explanations

    loading, returning, or adding items

    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
     fair
    -0.08
    çĪ±äºº
    -0.07
    å¼Ģèĥĥ
    -0.07
    errick
    -0.07
    aab
    -0.06
    uke
    -0.06
    endregion
    -0.06
    yak
    -0.06
    obl
    -0.06
     stor
    -0.06
    POSITIVE LOGITS
    åĨį次
    0.12
    again
    0.11
     again
    0.11
    _again
    0.11
     erneut
    0.10
     novamente
    0.10
    éĩįæĸ°
    0.10
     Again
    0.10
    åĨį度
    0.10
    Again
    0.10
    Activations Density 0.090%

    No Known Activations