© 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. 54932
    Prev
    Next
    INDEX
    Explanations

    html table row

    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
    imar
    -0.07
    polator
    -0.06
    大æĤ²
    -0.06
    åľ¨å¿ħ
    -0.06
    inaire
    -0.06
    ĵĺ
    -0.06
    alli
    -0.06
    ặn
    -0.06
    ç¾¤å²Ľ
    -0.06
    æĽ´å¹¿
    -0.06
    POSITIVE LOGITS
    .Row
    0.10
     row
    0.10
    -row
    0.09
    TableRow
    0.09
     TableRow
    0.09
     DataRow
    0.09
     rows
    0.09
    .Rows
    0.09
    à¹ģà¸ĸว
    0.09
    .getRow
    0.09
    Activations Density 0.126%

    No Known Activations