© 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. 55010
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
    ãĤĪãģĨãģª
    -0.08
    èĺĭ
    -0.08
    ä»ĸåij½
    -0.08
    ìłķíķľ
    -0.08
    inch
    -0.07
    ways
    -0.07
    ignon
    -0.07
    ings
    -0.07
    аÑĢа
    -0.07
    æĢ§åľ°
    -0.07
    POSITIVE LOGITS
    Ïĩη
    0.08
     Plen
    0.08
     ÃŃch
    0.07
    acular
    0.07
    rif
    0.07
    uxtap
    0.07
    ÏĨι
    0.07
    ominated
    0.06
    okia
    0.06
    ذاÙĥ
    0.06
    Activations Density 0.081%

    No Known Activations