© 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. 8936
    Prev
    Next
    INDEX
    Explanations

    data reports and statistics

    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
    å·¥ä½ľå¹´éĻIJ
    -0.07
    身份çļĦ
    -0.07
    éķ¿çº¦
    -0.07
    quia
    -0.06
    .utility
    -0.06
    æłĩè¯Ĩçłģ
    -0.06
    åĩºèº«çļĦ
    -0.06
    orne
    -0.06
    orte
    -0.06
    bidden
    -0.06
    POSITIVE LOGITS
    _report
    0.09
     report
    0.09
    è¿ĻäºĽæķ°æį®
    0.09
     computed
    0.09
    æĬ¥åijĬ
    0.08
     aggreg
    0.08
     aggregated
    0.08
     calculated
    0.08
    raw
    0.08
     reports
    0.08
    Activations Density 0.225%

    No Known Activations