© 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. 45738
    Prev
    Next
    INDEX
    Explanations

    license or ephemera

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.10
    .ptr
    -0.07
    æ³¥
    -0.07
    blatt
    -0.07
    çľ
    -0.07
    èĽ
    -0.07
    åĩºå¤´
    -0.06
    armi
    -0.06
    ston
    -0.06
    оби
    -0.06
    POSITIVE LOGITS
    agens
    0.10
    éĥ¨åĴĮ
    0.08
    iversal
    0.07
    åĴĮ好
    0.07
    åĴĮçĪ±
    0.07
    绿水
    0.07
     vá»įng
    0.07
    åĴĮåįİ
    0.07
    èķĬ
    0.07
    ä»Ļåīij
    0.07
    Activations Density 0.245%

    No Known Activations