© 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. 7169
    Prev
    Next
    INDEX
    Explanations

    time delay and calculation

    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
    _abort
    -0.08
     ext
    -0.07
    æľīæĥħ
    -0.07
    cha
    -0.07
    ensä
    -0.07
     Ø£ÙĪÙĦÙī
    -0.07
    Abort
    -0.07
     cl
    -0.06
    ä¸Ńèĭ±æĸĩ
    -0.06
    åħ¸
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ħียà¸ĩ
    0.07
    æ¥ł
    0.07
    ÑĢеб
    0.07
    ifax
    0.07
    第äºĮæĿ¡
    0.07
     comparison
    0.07
    vergleich
    0.07
    asca
    0.07
    loth
    0.07
    åħ¶è§ĤçĤ¹
    0.07
    Activations Density 0.041%

    No Known Activations