© 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. 44327
    Prev
    Next
    INDEX
    Explanations

    tokens before "to" or "of"

    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
    éĴ¦
    -0.08
    reopen
    -0.08
    ä¹ĭé¤ĺ
    -0.07
    .Encode
    -0.07
    ogan
    -0.07
    ä¸ĭè§Ĵ
    -0.07
    _NOP
    -0.07
    å¾·åįİ
    -0.07
    **–
    -0.07
    榴
    -0.07
    POSITIVE LOGITS
    æŀľçľŁ
    0.08
    éĤ£è¾¹
    0.07
     prima
    0.07
    æŀľçĦ¶
    0.06
    iril
    0.06
     ÑıкобÑĭ
    0.06
    ä¹ĭç±»çļĦ
    0.06
    ä¹ĭç±»
    0.06
    èĭ¦èĭ¦
    0.06
    æµģåħī
    0.06
    Activations Density 0.003%

    No Known Activations