© 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. 51319
    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
    幸
    -0.08
    imson
    -0.07
     Buon
    -0.07
    etano
    -0.07
    çĶļèĢħ
    -0.07
    è¿Ľè¡ĮéĢīæĭ©
    -0.07
    inkan
    -0.07
    ualan
    -0.07
    @author
    -0.07
    ihan
    -0.07
    POSITIVE LOGITS
    ä¸ĢæŃ¥æŃ¥
    0.07
    好åŃ©åŃIJ
    0.07
    æ¸ħæ¥ļåľ°
    0.07
    âĢ¦I
    0.07
    è·¯éĢı
    0.07
    ÙĨاÙĩ
    0.06
    æīİå®ŀ
    0.06
    æīİå®ŀçļĦ
    0.06
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.06
    æħ¢æħ¢
    0.06
    Activations Density 0.000%

    No Known Activations