© 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. 51934
    Prev
    Next
    INDEX
    Explanations

    organic compounds and molecules

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å·¥ä½ľä¸ĬçļĦ
    -0.07
    ocre
    -0.07
    mgr
    -0.07
     Artis
    -0.07
    åħį
    -0.07
    udging
    -0.07
    éĿĴæĿ¾
    -0.07
     NSK
    -0.07
    人社éĥ¨
    -0.07
    ensem
    -0.07
    POSITIVE LOGITS
     mạch
    0.10
    åĪĨåŃIJ
    0.09
     molecules
    0.08
     molecule
    0.08
    çĥĥ
    0.08
     structures
    0.08
     molecular
    0.08
     ÑģÑĤÑĢоениÑı
    0.08
    骨æŀ¶
    0.08
     ethanol
    0.08
    Activations Density 0.033%

    No Known Activations