© 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. 55507
    Prev
    Next
    INDEX
    Explanations

    qualities and conditions

    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
    åħ¨éĥ¨è¯Ħ论
    -0.08
    .argument
    -0.07
    ä¸įè¦ģåIJĥ
    -0.07
     Mittelpunkt
    -0.07
    udem
    -0.07
     >&
    -0.07
    声éģĵ
    -0.07
    echt
    -0.06
    æį®æѤæĵįä½ľ
    -0.06
    leid
    -0.06
    POSITIVE LOGITS
    less
    0.09
    -less
    0.09
    æŁIJäºĽ
    0.08
    åľ¨æŁIJäºĽ
    0.08
    åıªä¸įè¿ĩæĺ¯
    0.08
    à¸ļà¹īาà¸ĩ
    0.08
    -ish
    0.07
    åıªä¸įè¿ĩ
    0.07
    lessness
    0.07
    æŁIJç§įç¨ĭ度ä¸Ĭ
    0.07
    Activations Density 0.068%

    No Known Activations