© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    geometric perspective

    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
    ç½ijé¦ĸ页
    -0.08
    olit
    -0.07
    ç®Ģ书
    -0.07
    æŀľçĦ¶æĺ¯
    -0.07
    羣çļĦ太
    -0.07
    羣çļĦæĺ¯
    -0.07
    羣æĺ¯
    -0.06
    ีà¸Ķ
    -0.06
    åıĬåħ¶
    -0.06
    artet
    -0.06
    POSITIVE LOGITS
    èĤ¡æĮĩ
    0.08
    [âĢ¦
    0.07
    eref
    0.07
    åį³åľ¨
    0.07
    èģĶå¸Ń
    0.07
    æĮĩçļĦ
    0.07
    ç»´ä¿®ä¿Ŀåħ»
    0.06
    åĪĻ该
    0.06
    ROP
    0.06
    ühl
    0.06
    Activations Density 0.015%

    No Known Activations