© 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. 59022
    Prev
    Next
    INDEX
    Explanations

    sorted by order

    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
    лок
    -0.08
    å¤Ħå¤Ħ
    -0.08
    ponge
    -0.08
    以ä¸ĭ为
    -0.08
    çĤ¹çĿĽ
    -0.08
    riez
    -0.08
    çijŀæĭī
    -0.08
     passata
    -0.08
    eree
    -0.08
    اتÙĬ
    -0.08
    POSITIVE LOGITS
    æİĴåºı
    0.10
     sorted
    0.10
     ascending
    0.09
    æİĴåĪĹ
    0.09
     order
    0.08
    sorted
    0.08
     descending
    0.08
     sorting
    0.08
    .sort
    0.08
    _sorted
    0.08
    Activations Density 0.035%

    No Known Activations