© 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. 59097
    Prev
    Next
    INDEX
    Explanations

    electrodes and electricity

    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
    æĵ¦èĤ©
    -0.07
    ë¦Ħ
    -0.07
    бол
    -0.07
    ä¸İåıijå±ķ
    -0.07
    æĺ¯äººçĶŁ
    -0.07
    ç´łæĿIJ
    -0.07
    ongi
    -0.07
    amas
    -0.07
    ä¸Ģç²Ĵ
    -0.07
    åı°çIJĥ
    -0.07
    POSITIVE LOGITS
     elect
    0.09
    çĶµ
    0.09
    elect
    0.08
    éĢļçĶµ
    0.08
    çļĦçĶµ
    0.08
    electric
    0.08
     electrodes
    0.08
     electricity
    0.08
     electrode
    0.08
     electric
    0.08
    Activations Density 0.065%

    No Known Activations