© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21789
    Prev
    Next
    INDEX
    Explanations

    assuming positive

    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
    æľĢåıĹ
    -0.08
    以æľĢ
    -0.07
    æľĢ为
    -0.07
    åħ¶ä¸Ń以
    -0.07
    åľ¨å¿ħ
    -0.07
    åħ¶ä¸ŃæľĢ
    -0.07
    ias
    -0.07
    æĺłåħ¥
    -0.06
    æľĢä¼ĺ
    -0.06
    æľĢä½İå·¥èµĦ
    -0.06
    POSITIVE LOGITS
    æĪ®
    0.08
    hofer
    0.08
    iddles
    0.08
    annen
    0.07
    inkt
    0.07
     belie
    0.07
    åŁ¹
    0.07
    peri
    0.07
    å·¾
    0.07
     Bale
    0.07
    Activations Density 0.002%

    No Known Activations