© 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. 59967
    Prev
    Next
    INDEX
    Explanations

    religious texts and teachings

    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
    æĽ¾çĶ¨åIJį
    -0.07
    ç§ģæľį
    -0.07
    åįĥåħĥ
    -0.07
    åıij表论æĸĩ
    -0.07
    åĨħçĶŁ
    -0.07
    éŁ
    -0.07
    é¦Ļè¾£
    -0.07
    arbe
    -0.06
     hopefully
    -0.06
     lag
    -0.06
    POSITIVE LOGITS
     seals
    0.08
     passages
    0.08
     Hebrew
    0.08
    èµIJ
    0.08
    å¤ļå¤Ħ
    0.08
    á¼IJ
    0.07
    åij¼
    0.07
    åIJ©åĴIJ
    0.07
     proph
    0.07
    tones
    0.07
    Activations Density 0.056%

    No Known Activations