© 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. 58982
    Prev
    Next
    INDEX
    Explanations

    graph, path, bus, vertices

    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
     volum
    -0.07
    æµ®
    -0.07
    éĶħçĽĸ
    -0.06
    æĸĻ
    -0.06
    vel
    -0.06
     floating
    -0.06
    é»į
    -0.06
    å¾®éĩı
    -0.06
    寸
    -0.06
    éļıå¿ĥæīĢ欲
    -0.06
    POSITIVE LOGITS
    nodoc
    0.09
    Vertices
    0.08
    vertices
    0.08
    纾
    0.08
    _nodes
    0.08
    åIJİåı°åĽŀå¤į
    0.08
     DISCLAIMER
    0.08
    -node
    0.08
    _verts
    0.07
    å§Ĭ妹
    0.07
    Activations Density 0.009%

    No Known Activations