© 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. 13135
    Prev
    Next
    INDEX
    Explanations

    whether, how, number, highest, sort

    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
    æİĸ
    -0.08
    æī¬æī¬
    -0.06
    åŁĥå°Ķ
    -0.06
    åıªæľīéĢļè¿ĩ
    -0.06
    :border
    -0.06
    old
    -0.06
    ä¸į好çľĭ
    -0.06
    é©®
    -0.06
    ritable
    -0.06
    angan
    -0.06
    POSITIVE LOGITS
    æŁIJä¸Ģ个
    0.08
    æŁIJæŁIJ
    0.08
    æŁIJç§į
    0.08
    æŁIJä¸Ģ天
    0.08
    æŁIJ人
    0.07
    åĵª
    0.07
    çī¹å®ļ
    0.07
    æŁIJ
    0.07
    æŁIJ个
    0.07
    ä»Ģä¹ĪçļĦ
    0.07
    Activations Density 0.014%

    No Known Activations