© 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. 63168
    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
    ossi
    -0.07
    æĸ°åįİ社记èĢħ
    -0.07
    å¿ĺè®°äºĨ
    -0.07
    ãģªãģĬ
    -0.07
    mega
    -0.06
    AYA
    -0.06
    EMAT
    -0.06
    dre
    -0.06
     retrait
    -0.06
    çŃ¹å»º
    -0.06
    POSITIVE LOGITS
     Pellegr
    0.07
    quite
    0.07
    ÑģÑĤоиÑĤ
    0.07
    åij¨ä¸Ģèĩ³åij¨äºĶ
    0.07
    inde
    0.07
    -pocket
    0.06
    -pagination
    0.06
    åģļèµ·æĿ¥
    0.06
    iture
    0.06
     Coun
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.