© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19242
    Prev
    Next
    INDEX
    Explanations

    action, campaigns, and petitions

    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
     تØŃÙĥÙħ
    -0.08
    欢è¿İä½ł
    -0.08
    åĽłæĿIJæĸ½æķĻ
    -0.07
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.07
    burgh
    -0.07
    ØŃÙĥÙħ
    -0.07
    æĭ¬
    -0.07
     bienvenida
    -0.07
    çĮľä½łåĸľæ¬¢
    -0.07
    åĸľè¿İ
    -0.06
    POSITIVE LOGITS
     advocacy
    0.11
     Advoc
    0.10
    åıij声
    0.10
     advocating
    0.10
     impass
    0.09
     activist
    0.09
    åĵ½åĴ½
    0.09
     crus
    0.09
     activism
    0.09
     silenced
    0.08
    Activations Density 0.455%

    No Known Activations