© 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. 4831
    Prev
    Next
    INDEX
    Explanations

    numbers followed by % or mA

    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
    Ö¼
    -0.10
    ulich
    -0.09
    crement
    -0.09
    culp
    -0.09
    pector
    -0.09
    à§įন
    -0.09
    à¯įà®ķ
    -0.09
    หà¹Į
    -0.08
    zelfde
    -0.08
    haft
    -0.08
    POSITIVE LOGITS
    icients
    0.08
    otent
    0.08
    ulent
    0.08
    igny
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    ity
    0.08
    å¾Ĺä¸Ĭ
    0.07
    lication
    0.07
    ÙĨÙĪاÙĨ
    0.07
    ness
    0.07
    Activations Density 0.172%

    No Known Activations