© 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. 27132
    Prev
    Next
    INDEX
    Explanations

    information following "that" is not English

    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
     -
    -0.07
     impre
    -0.07
    ç§ijæĻ®
    -0.06
    ummy
    -0.06
    igna
    -0.06
    åĪ°åºķ
    -0.06
    ä¾ĿéĻĦ
    -0.06
    йма
    -0.06
     uns
    -0.06
    ä¸įæ¼ı
    -0.06
    POSITIVE LOGITS
    illion
    0.10
    оÑĢе
    0.09
    ids
    0.09
    æį·
    0.08
    acho
    0.08
    èµ°ä¸Ģèµ°
    0.08
    ván
    0.08
    eer
    0.08
    æĿ¥äºº
    0.08
    жин
    0.08
    Activations Density 0.021%

    No Known Activations