© 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. 21359
    Prev
    Next
    INDEX
    Explanations

    mission, charter, or constitution

    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
    émon
    -0.08
     Garan
    -0.08
    å¿ĥä¸Ńæľīæķ°
    -0.07
    æv
    -0.07
    fiz
    -0.07
    mano
    -0.07
    æĥ³åĩº
    -0.07
    _MANY
    -0.07
    urun
    -0.07
    大èĩ´
    -0.07
    POSITIVE LOGITS
    ç²¾ç¥ŀåĴĮ
    0.08
    çĪ±å²Ĺæķ¬ä¸ļ
    0.07
     latest
    0.07
     intents
    0.07
    ä¼ļ议精ç¥ŀ
    0.07
    stras
    0.07
    æĮĩ示精ç¥ŀ
    0.07
    è¯»æľ¬
    0.07
    -ren
    0.07
    åĴĮæľ¬
    0.07
    Activations Density 0.045%

    No Known Activations