© 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. 15524
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    ä¸įçŁ¥éģĵ为ä»Ģä¹Ī
    -0.07
    leon
    -0.07
    imei
    -0.06
    è¾ħ以
    -0.06
    etti
    -0.06
     Ùħرد
    -0.06
    ucci
    -0.06
    åĽĽéĢļ
    -0.06
    å©·å©·
    -0.06
    åŁºå°¼
    -0.06
    POSITIVE LOGITS
    voi
    0.07
    æľīéģĵ
    0.07
    ivs
    0.07
     ÑĢеÑĪа
    0.07
    è¨Ģ
    0.07
    ÙİاÙĩ
    0.07
    æ¶ĪåĮĸéģĵ
    0.07
    å¼ı
    0.07
    endale
    0.06
    кин
    0.06
    Activations Density 0.500%

    No Known Activations