© 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. 44633
    Prev
    Next
    INDEX
    Explanations

    proton and hydrogen transport

    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
    nage
    -0.07
    å¨Ł
    -0.07
     Oilers
    -0.07
    NÄIJ
    -0.07
    åıijçĶŁæĦıå¤ĸ
    -0.07
    客æ°Ķ
    -0.07
    à¬Ľ
    -0.07
    eland
    -0.07
    äºĴ帮
    -0.07
    æµ·éĩĮ
    -0.07
    POSITIVE LOGITS
     Pram
    0.07
    èħ»
    0.06
    íĮ©
    0.06
    iture
    0.06
    _reduce
    0.06
    intang
    0.06
     reduction
    0.06
    ä¸įè§ī
    0.06
     summoned
    0.05
    æŶ令
    0.05
    Activations Density 0.004%

    No Known Activations