© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23127
    Prev
    Next
    INDEX
    Explanations

    voting and proportional representation

    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
    IGIN
    -0.07
    èIJ¥ä¸ļæľŁéĻIJ
    -0.07
    åŁºæľ¬æĬĢèĥ½
    -0.07
    ä¼´ä½ł
    -0.06
    æľīç¼ĺ
    -0.06
    Verb
    -0.06
    ä¸Ģå¼ı
    -0.06
    æĮijæĪĺæĢ§
    -0.06
    ØŃض
    -0.06
     Stellen
    -0.06
    POSITIVE LOGITS
     ballots
    0.11
     voting
    0.11
     votes
    0.10
     rankings
    0.10
     ranking
    0.10
    票
    0.10
     vote
    0.09
     Voting
    0.09
     ballot
    0.09
     voter
    0.09
    Activations Density 0.024%

    No Known Activations