© 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. 32357
    Prev
    Next
    INDEX
    Explanations

    conditional checking

    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
    ç½ijå°ıç¼ĸ
    -0.08
    lest
    -0.08
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    -0.08
    SCII
    -0.08
    ק×ķת
    -0.07
    太大äºĨ
    -0.07
    },{"
    -0.07
    ULT
    -0.07
    好åĥıæĺ¯
    -0.07
    ä»Ļåīij
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.08
    并ä¸Ķ
    0.07
    èĢĮä¸Ķ
    0.07
    éĤ£ä¹Īå°±
    0.07
    endan
    0.07
     anymore
    0.07
    urian
    0.07
    æĢİä¹ĪåĬŀ
    0.06
     &&
    0.06
    asel
    0.06
    Activations Density 0.023%

    No Known Activations