© 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. 24801
    Prev
    Next
    INDEX
    Explanations

    dream come true

    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
    åĴĮè°ĥæķ´
    -0.09
    tright
    -0.08
    [Test
    -0.07
    /edit
    -0.07
    amen
    -0.07
    éĢģä½ł
    -0.07
    <decltype
    -0.07
    èĬ®
    -0.07
     bikin
    -0.07
    æĹ¥åĪ¶
    -0.07
    POSITIVE LOGITS
    被
    0.09
    å®ĮæĪIJæĥħåĨµ
    0.09
    被æīĵ
    0.09
    è¦ģ被
    0.09
    è¢«ä½ł
    0.08
    éĥ½ä¼ļ被
    0.08
     fulfilled
    0.08
     satisfied
    0.08
    à¹Ħà¸Ķà¹īรัà¸ļà¸ģาร
    0.08
    ä¹Łæľī人
    0.08
    Activations Density 0.411%

    No Known Activations