© 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. 65188
    Prev
    Next
    INDEX
    Explanations

    difference, fix, primarily

    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
    hurst
    -0.07
    ä¸īæĸ¹
    -0.07
    mite
    -0.07
    /bower
    -0.07
    ä¸ī线
    -0.07
    ymar
    -0.07
    uchen
    -0.07
    _profiles
    -0.06
     profil
    -0.06
    igm
    -0.06
    POSITIVE LOGITS
    主è¦ģæĺ¯
    0.17
     primarily
    0.16
     mainly
    0.16
    主è¦ģå°±æĺ¯
    0.15
     chiefly
    0.15
    主è¦ģ表çݰ为
    0.14
    主è¦ģ为
    0.14
    主è¦ģä½ĵçİ°åľ¨
    0.14
    主è¦ģåľ¨
    0.13
     principally
    0.13
    Activations Density 0.318%

    No Known Activations