© 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. 65312
    Prev
    Next
    INDEX
    Explanations

    legally reported

    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
    以ä¸Ĭå°±æĺ¯
    -0.09
    æľĢåIJİæĺ¯
    -0.08
    å°±è¿Ļæł·
    -0.08
    iah
    -0.07
    æľĢåIJİçļĦ
    -0.07
    ulg
    -0.07
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.07
    è¿ĺæľī个
    -0.07
     Lastly
    -0.07
    igura
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪéľĢè¦ģ
    0.11
    é¦ĸåħĪåľ¨
    0.09
     dulu
    0.08
     zunächst
    0.08
    é¦ĸåħĪ
    0.07
     first
    0.07
     Zunächst
    0.07
     ãģ¾ãģļ
    0.07
    åij±
    0.07
     Ø£ÙĪÙĦاÙĭ
    0.07
    Activations Density 0.149%

    No Known Activations