© 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. 61524
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ§Ľ
    -0.08
    kest
    -0.08
    rit
    -0.07
     Cinder
    -0.07
    zyn
    -0.07
    ä¸įéļ¾çľĭåĩº
    -0.07
    åı¯ä»¥çIJĨ解
    -0.06
    ugin
    -0.06
    ardu
    -0.06
    çľĭå¾ĹåĩºæĿ¥
    -0.06
    POSITIVE LOGITS
    UpDown
    0.08
    ิà¹īà¸Ļ
    0.08
    ilib
    0.07
    áŀ½
    0.07
    æ°´çģ«
    0.07
    scribed
    0.07
    åĽº
    0.07
     Jus
    0.07
    èĩªå·±æīĢ
    0.07
    _subtitle
    0.06
    Activations Density 0.000%

    No Known Activations