© 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. 56086
    Prev
    Next
    INDEX
    Explanations

    or rather

    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
    ingga
    -0.07
     Suy
    -0.07
    æ¯Ķå¦Ĥåľ¨
    -0.07
    è¯ķçĤ¹å·¥ä½ľ
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    atabase
    -0.07
    åıĪä¼ļ
    -0.07
    ÑħÑĢа
    -0.07
     wiederum
    -0.07
    bm
    -0.06
    POSITIVE LOGITS
    åī
    0.07
    æİ
    0.07
    åĵ
    0.07
    à¹Ģà¸īà¸ŀาะ
    0.07
    å¢ĥ
    0.06
    èĤł
    0.06
    è¾Ĺ
    0.06
    igned
    0.06
    oters
    0.06
    çĮ
    0.06
    Activations Density 0.243%

    No Known Activations