© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    stated that

    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
    åĸĿ彩
    -0.09
    anner
    -0.07
     Vest
    -0.07
    vest
    -0.07
    íĥģ
    -0.07
    edList
    -0.07
    横è¡Į
    -0.06
    ãģĦãģ¾ãģĽãĤĵãģĭ
    -0.06
    ä¸Ĭæ¼Ķ
    -0.06
    çļĦ主è§Ĵ
    -0.06
    POSITIVE LOGITS
    éĩĩ访ä¸Ń
    0.09
     candid
    0.09
     interview
    0.08
    è°ĪåıĬ
    0.08
     interviews
    0.08
    çŁ¢
    0.08
     articul
    0.08
    访è°Ī
    0.08
    æĺİç¡®
    0.08
    æĺİ确表示
    0.08
    Activations Density 0.552%

    No Known Activations