© 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. 47752
    Prev
    Next
    INDEX
    Explanations

    energy transformation

    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
    æľĽè¿ľ
    -0.09
     sekalipun
    -0.09
    ÙĤÙĬب
    -0.08
    زاÙĦ
    -0.08
    heb
    -0.08
    æķ°æį®æĿ¥æºIJ
    -0.08
    ãģĹãģĮ
    -0.08
    åĪ¶çļĦ
    -0.08
    LOCKS
    -0.08
    awang
    -0.08
    POSITIVE LOGITS
    æļĤæŶçļĦ
    0.07
    ilent
    0.06
    çŃīå½¢å¼ı
    0.06
    åıĬåħ¶å®ĥ
    0.06
    è¤ļ
    0.06
     eventual
    0.06
    /from
    0.06
    表çİ°åĩºæĿ¥çļĦ
    0.06
    åıĬåħ¶ä»ĸ
    0.06
     eventually
    0.06
    Activations Density 0.010%

    No Known Activations