© 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. 3438
    Prev
    Next
    INDEX
    Explanations

    propose to

    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
    åı£çļĦ
    -0.09
    ìĭľíĤ¤
    -0.08
    à¸ŀà¸Ń
    -0.08
    à§įম
    -0.08
    sache
    -0.08
    è¦ģæ±Ĥèĩªå·±
    -0.08
     Äijáo
    -0.08
    acias
    -0.08
     Premiership
    -0.08
    à¹Ģà¸Ľà¸¥à¹Īา
    -0.08
    POSITIVE LOGITS
    ç¾²
    0.08
    ative
    0.07
     вниманиÑİ
    0.07
    à¹ģà¸Ļะ
    0.07
    escu
    0.07
    ëĮĢë¡ľ
    0.07
    æĸ°çļĦ
    0.07
    à¹ĥหà¹īมีà¸ģาร
    0.07
    idon
    0.07
    ÏĦαι
    0.07
    Activations Density 0.042%

    No Known Activations