© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39379
    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
    irman
    -0.08
    ä¸Ģæĸ°
    -0.08
    yan
    -0.07
    åĮĸ管çIJĨ
    -0.07
    uell
    -0.07
    iele
    -0.07
    ewnÄĻ
    -0.07
     Silvio
    -0.06
    heimer
    -0.06
    åºĶä¿ĿæĮģ
    -0.06
    POSITIVE LOGITS
    itals
    0.07
    uta
    0.07
    ละ
    0.07
    athi
    0.07
    ĸ
    0.06
     volna
    0.06
    meld
    0.06
     latter
    0.06
    æ·
    0.06
    /loader
    0.06
    Activations Density 0.000%

    No Known Activations