© 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. 37538
    Prev
    Next
    INDEX
    Explanations

    path separators, symbols, and logical connectors

    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
    gade
    -0.08
    缸åħ³éĹ®çŃĶ
    -0.08
    каÑĤа
    -0.07
    awk
    -0.07
    à¹Īย
    -0.07
    getDefault
    -0.07
    ä¸įéĹ®
    -0.07
    walt
    -0.07
    irk
    -0.07
    .lat
    -0.07
    POSITIVE LOGITS
    çŃīçŃī
    0.10
     etc
    0.09
    æĢ»ä¹ĭ
    0.08
    æĢ»èĢĮè¨Ģä¹ĭ
    0.08
    çľĭå¾Ĺ
    0.07
     sebagainya
    0.07
     bref
    0.06
    çĦ¶
    0.06
    è¿ĻäºĽéĥ½
    0.06
    稽
    0.06
    Activations Density 0.002%

    No Known Activations