© 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. 12524
    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
    èĴĻ
    -0.06
    寥寥
    -0.06
    奴
    -0.06
    ä¸įäºĨå¤ļä¹ħ
    -0.06
    æĬķèµĦä»·åĢ¼
    -0.06
     Selv
    -0.06
     Improvement
    -0.06
    aine
    -0.06
    è¿Ļä¸ªæł·åŃIJ
    -0.06
    ç´«åħī
    -0.06
    POSITIVE LOGITS
    éĹ®åĮ»çĶŁ
    0.09
    çĻ¾åIJį
    0.08
    éĢļåĪĻ
    0.08
     niá»ĩm
    0.07
    ross
    0.07
     inv
    0.07
    mä
    0.07
    Callable
    0.07
    ffffffff
    0.07
    su
    0.07
    Activations Density 0.000%

    No Known Activations