© 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. 39180
    Prev
    Next
    INDEX
    Explanations

    specifically

    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
    moni
    -0.08
    alda
    -0.08
    åıĪå¦Ĥ
    -0.08
    æĢ»ä¹ĭ
    -0.08
    imetr
    -0.07
    ä¸ĭä¸Ģ个
    -0.07
     beware
    -0.07
    rede
    -0.07
    twig
    -0.07
    िय
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵæĿ¥è¯´
    0.12
    ä¹Łå°±æĺ¯è¯´
    0.12
     Specifically
    0.11
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.10
    è¿Ļæĺ¯åĽłä¸º
    0.10
    è¿ĻæĦıåij³çĿĢ
    0.10
     specifically
    0.09
    æį¢åı¥è¯Ŀ说
    0.09
    ä¹Łå°±æĺ¯
    0.08
    ä¾ĭå¦Ĥ
    0.08
    Activations Density 0.299%

    No Known Activations