© 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. 33254
    Prev
    Next
    INDEX
    Explanations

    entanglement

    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
    à¸Ĭà¸Ļ
    -0.08
    vere
    -0.08
    suming
    -0.08
    itrine
    -0.08
    åı¸éķ¿
    -0.08
    aturas
    -0.08
     eget
    -0.07
    çݯ线
    -0.07
    EDURE
    -0.07
    åºĶå¾ģ
    -0.07
    POSITIVE LOGITS
    èµ·æĿ¥çļĦ
    0.07
    æľĢæ·±
    0.07
    ระหวà¹Īาà¸ĩ
    0.07
    èµ·æĿ¥
    0.07
    纽
    0.07
    çĶŁæŃ»
    0.07
     sẵn
    0.07
    between
    0.07
    hips
    0.07
    ä¸İ被
    0.07
    Activations Density 0.005%

    No Known Activations