© 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. 621
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun or date

    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
    åIJĵ人
    -0.07
    ä¸İåīį
    -0.07
    åı¬
    -0.07
    ä¸ĢæľĿ
    -0.07
    为è°ģ
    -0.07
    æĺŃ
    -0.07
    æľ¬ç«ĻæīĢæľī
    -0.07
    éĻ¤ä»¥
    -0.07
    ä¸İçłĶ究
    -0.07
    æĹłæīĢè°ĵ
    -0.07
    POSITIVE LOGITS
    è¦ģæ±Ĥåħ¶
    0.11
    åIJİèĢħ
    0.11
    enet
    0.09
    åħ³ç³»
    0.08
    via
    0.08
    æīĵæĪIJ
    0.08
    éĹ´æİ¥
    0.08
    为åħ¶
    0.08
    åħ³ç³»ä¸Ń
    0.08
    让åħ¶
    0.08
    Activations Density 0.707%

    No Known Activations