© 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. 64215
    Prev
    Next
    INDEX
    Explanations

    preceding punctuation or separators like $, ..., &

    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
    oly
    -0.06
    çIJĨæīĢå½ĵçĦ¶
    -0.06
    顺åı£
    -0.06
    åģļä¸ĢåIJį
    -0.06
    âĢ
    -0.06
    产åĵģåı¬åĽŀ
    -0.06
    åľ¨è¿Ļä¸Ģ
    -0.06
    æĶ»åŁİ
    -0.06
    ãĢĢ
    -0.05
    èĮµ
    -0.05
    POSITIVE LOGITS
    亦çĦ¶
    0.10
    åIJĮçIJĨ
    0.09
    emente
    0.09
     likewise
    0.08
    ä¹Łæĺ¯å¦ĤæѤ
    0.08
     similarly
    0.08
    çī¹æ®ĬæĢ§
    0.08
    ãģĵãģ¡ãĤīãģ¯
    0.08
     нÑĥ
    0.08
     наобоÑĢоÑĤ
    0.08
    Activations Density 0.031%

    No Known Activations