© 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. 55044
    Prev
    Next
    INDEX
    Explanations

    direction prepositions to/into

    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
    çĶµè¯ĿèģĶç³»
    -0.07
    åĽŀæĿ¥äºĨ
    -0.07
    igh
    -0.06
     باÙĦÙĨسبة
    -0.06
    ie
    -0.06
    å¾·éŁ³
    -0.06
    åĩłå¹´æĿ¥
    -0.06
    åݨæĪ¿éĩĮ
    -0.06
    åĽŀåĪ°äºĨ
    -0.06
    è¿ľçľº
    -0.06
    POSITIVE LOGITS
    /from
    0.14
     unsus
    0.11
    æľīéľĢè¦ģçļĦ
    0.10
     ÙĪØ¥ÙĦÙī
    0.09
     través
    0.09
     vÃŃa
    0.09
     needy
    0.09
    å®ŀå¤Ħ
    0.09
    å¿ĥ仪
    0.08
    çļĦåIJĦ个
    0.08
    Activations Density 0.297%

    No Known Activations