© 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. 13436
    Prev
    Next
    INDEX
    Explanations

    financial terms and agreements

    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
    åŃ£æĬ¥
    -0.08
    accumulator
    -0.08
    年审
    -0.08
     yearly
    -0.08
    accum
    -0.08
    rug
    -0.07
    egel
    -0.07
    annual
    -0.07
     annual
    -0.07
     Accum
    -0.07
    POSITIVE LOGITS
    æİ¥åıĹ
    0.07
    åħ¬åħģä»·åĢ¼
    0.07
    uen
    0.07
    ibri
    0.07
    ç¡®å®ļçļĦ
    0.07
    æİ¥åıĹäºĨ
    0.07
    å·¥åħ·çļĦ
    0.07
    ä¸įå¾Ĺä½İäºİ
    0.07
    ç¡®å®ļ
    0.07
    ç½®æį¢
    0.07
    Activations Density 0.002%

    No Known Activations