© 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. 44519
    Prev
    Next
    INDEX
    Explanations

    regularly. files, items, HP

    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
    ortable
    -0.07
     infatti
    -0.07
    bjerg
    -0.07
    èħ
    -0.07
    éī
    -0.06
    注
    -0.06
    å¾ĭå·±
    -0.06
     enim
    -0.06
    iges
    -0.06
    anges
    -0.06
    POSITIVE LOGITS
    åıªæĺ¯ä¸ºäºĨ
    0.08
    顶ä¸Ĭ
    0.08
    çĦ¶åIJİåĨį
    0.08
    å°±ç®ĹäºĨ
    0.07
     magari
    0.07
    åħ¶ä»ĸåľ°æĸ¹
    0.07
     või
    0.07
    æł·åŃIJ
    0.07
    ä¹ħèĢĮä¹ħä¹ĭ
    0.07
    jach
    0.07
    Activations Density 0.016%

    No Known Activations