© 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. 4818
    Prev
    Next
    INDEX
    Explanations

    im/overlay related to layering

    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
    olong
    -0.08
    ë¦Ħ
    -0.08
     distant
    -0.08
    ؤÙĦ
    -0.08
    illard
    -0.07
    atezza
    -0.07
    天边
    -0.07
    çĤ¬
    -0.07
    ettino
    -0.07
    PointF
    -0.07
    POSITIVE LOGITS
    åıł
    0.11
    à¸ĭà¹īà¸Ńà¸Ļ
    0.10
     layer
    0.10
     layers
    0.10
    åıłåĬł
    0.10
    äºĨä¸Ģå±Ĥ
    0.09
    çĸĬ
    0.09
    ä¸Ģå±Ĥ
    0.09
    layer
    0.09
     Layer
    0.09
    Activations Density 0.061%

    No Known Activations