© 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. 1873
    Prev
    Next
    INDEX
    Explanations

    is not

    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
    æĺ¯ä¸ĢåĪĩ
    -0.08
    åĽłä¸ºè¿Ļ个
    -0.08
    quisitions
    -0.08
     Waist
    -0.08
    everything
    -0.08
    ĴĪ
    -0.08
    ignon
    -0.08
    pector
    -0.08
    ä½¼
    -0.07
    ackson
    -0.07
    POSITIVE LOGITS
    ness
    0.06
    oken
    0.06
    åİŁæľīçļĦ
    0.06
    åİŁæľī
    0.06
    çļĦèĬ±
    0.06
     Raya
    0.06
    寿
    0.06
    orsk
    0.06
    unders
    0.06
    åİŁæĿ¥æĺ¯
    0.06
    Activations Density 0.001%

    No Known Activations