© 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. 16309
    Prev
    Next
    INDEX
    Explanations

    politics, party, member

    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
    nze
    -0.08
    ä½ļ
    -0.07
    æļĩ
    -0.07
    almas
    -0.07
    ç»ĥå°±
    -0.07
     anonym
    -0.07
    æĵĤ
    -0.07
    åįĹèĩ³
    -0.07
    ç¼Ń
    -0.07
    çŃīåľ°
    -0.07
    POSITIVE LOGITS
    -dominated
    0.10
    -leaning
    0.09
    ç³»ãģ®
    0.09
     ê³ĦìĹ´
    0.08
    为主ä½ĵçļĦ
    0.08
    主åĬŀçļĦ
    0.08
    -led
    0.08
    åĴĮéĿŀ
    0.07
    为主çļĦ
    0.07
    ạt
    0.07
    Activations Density 0.188%

    No Known Activations