© 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. 25586
    Prev
    Next
    INDEX
    Explanations

    know this if question

    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
    对ä¸ĢäºĽ
    -0.07
    对éĤ£äºĽ
    -0.07
    èĢĮéĤ£äºĽ
    -0.07
    schlä
    -0.07
    éĢĢæį¢
    -0.07
    æ£ł
    -0.07
    对äºİéĤ£äºĽ
    -0.07
    ArrayType
    -0.07
    à¸Ĺร
    -0.07
    åıĪå¼Ģå§ĭ
    -0.07
    POSITIVE LOGITS
    çļĦä½įç½®
    0.09
    ä»ĭçŁ³
    0.08
    ä½įç½®
    0.08
    æĮĩå®ļ
    0.08
     position
    0.08
    ä½įç½®çļĦ
    0.08
    å®ļçĤ¹
    0.08
    åIJįåŃĹ
    0.08
    à¸ķำà¹ģหà¸Ļà¹Īà¸ĩ
    0.07
    æĮĩå®ļçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations