© 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. 4691
    Prev
    Next
    INDEX
    Explanations

    downhole, colonial, native heart, offer, systems, lever, trends, settings

    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
    oura
    -0.08
    cium
    -0.07
    ovnÃŃ
    -0.07
    åĪ¹éĤ£éĹ´
    -0.07
     apt
    -0.07
     appunto
    -0.06
    æļĤè¡Įè§Ħå®ļ
    -0.06
    çŃīä¸ĢäºĽ
    -0.06
    pg
    -0.06
    ìĸ´ë¯¼
    -0.06
    POSITIVE LOGITS
    稿
    0.07
    ìĹŃ
    0.06
    kbd
    0.06
    ä¸ģ寧ãģ«
    0.06
    å°ıæķħäºĭ
    0.06
    ñez
    0.06
    ฯ
    0.06
    nty
    0.06
    olle
    0.06
    ñana
    0.06
    Activations Density 3.260%

    No Known Activations