© 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. 32810
    Prev
    Next
    INDEX
    Explanations

    listing number or letter options

    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
    åĦ¿çļĦ
    -0.09
    enda
    -0.08
    åĽ½åħ¬
    -0.08
    ugat
    -0.08
    awas
    -0.08
    åĦ¿
    -0.08
    wali
    -0.07
    åĴļ
    -0.07
    WebResponse
    -0.07
    èİ«
    -0.07
    POSITIVE LOGITS
    opper
    0.06
    该åħ¬åı¸çļĦ
    0.06
    为ä»Ģä¹Īä¼ļ
    0.06
    èĭ¥åľ¨
    0.06
     why
    0.06
    åįĹ
    0.06
    opan
    0.06
    pj
    0.05
    ä¸Ĭçļ®
    0.05
    该åħ¬åı¸
    0.05
    Activations Density 0.003%

    No Known Activations