© 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. 28055
    Prev
    Next
    INDEX
    Explanations

    titles and specific names

    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
    éĹ®é¢ĺæŶ
    -0.09
    å±ħæ°ijçļĦ
    -0.08
    çĶ±çľģ
    -0.07
    ouvre
    -0.07
    ä¹ŁæĮº
    -0.07
    ç¥ŀä¹ĭ
    -0.07
    uku
    -0.07
    غد
    -0.07
    %D
    -0.07
    å¸Ĥæ°ijçļĦ
    -0.07
    POSITIVE LOGITS
    ç³»ç»Łå°Ĩ
    0.09
    è§ĦèĮĥè¦ģæ±Ĥ
    0.08
    )[-
    0.07
    åħ¬åı¸å°Ĩ
    0.07
    æĸ¹åı¯
    0.07
    è¦ģæ±Ĥåľ¨
    0.07
    áĥĽáĥIJ
    0.07
    éĥ¨å°±
    0.07
    åľ°åĿĢä½įäºİ
    0.07
    æľīæķĪæľŁèĩª
    0.07
    Activations Density 0.528%

    No Known Activations