© 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. 57558
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or functions

    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
    èĥİ
    -0.07
    åĮĸå¤ĦçIJĨ
    -0.07
    ä¸ĩåĽ½
    -0.07
    çĻ¾èĬ±
    -0.07
    thesize
    -0.07
     ë¹
    -0.07
    å¦ĤæĦı
    -0.06
    udge
    -0.06
     inse
    -0.06
    天ä¸ĭ第ä¸Ģ
    -0.06
    POSITIVE LOGITS
    ä½ĻçĶŁ
    0.09
    æ®ĭ
    0.07
    antau
    0.07
    佬
    0.07
    æ®ĺ
    0.07
    漫漫
    0.07
    æ®ĭ渣
    0.07
     lév
    0.07
    ANTA
    0.07
    akai
    0.07
    Activations Density 0.004%

    No Known Activations