© 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. 41230
    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
    éŃĦ
    -0.07
    icket
    -0.07
    åħ¶éģĵ
    -0.07
    æł¼åħ°
    -0.07
    apati
    -0.07
    atron
    -0.07
    roker
    -0.07
    urier
    -0.07
     ÑģвоеобÑĢаз
    -0.07
    å¤ļç§įæĸ¹å¼ı
    -0.06
    POSITIVE LOGITS
    æīĵåıij
    0.08
    çĽĶ
    0.07
    koh
    0.07
    åıĬæĹ¶è§£åĨ³
    0.07
    ãģŁãĤī
    0.07
    tops
    0.07
    饶
    0.07
    ago
    0.07
    ÙĩÙIJ
    0.07
     surv
    0.07
    Activations Density 0.000%

    No Known Activations