© 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. 34665
    Prev
    Next
    INDEX
    Explanations

    countries, regions, sectors

    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
    çĴĭ
    -0.10
    ç±į
    -0.07
    libs
    -0.07
    izio
    -0.07
    rio
    -0.06
    åĵ²
    -0.06
    åįģç«ł
    -0.06
    ÃŃdia
    -0.06
    eller
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    POSITIVE LOGITS
    aha
    0.07
    çŁ¢
    0.07
    htable
    0.07
    abbo
    0.07
    ascÄĥ
    0.06
    igin
    0.06
    akening
    0.06
     larg
    0.06
     McGu
    0.06
    çľĭä¸įæĩĤ
    0.06
    Activations Density 0.058%

    No Known Activations