© 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. 49374
    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
    engel
    -0.07
    åľ°ä¸»
    -0.07
    anon
    -0.07
    ëĭ¨ìĿ´
    -0.07
    æĺĤ
    -0.07
     supposedly
    -0.06
    èŀ
    -0.06
    à¸ĩ
    -0.06
    eman
    -0.06
    este
    -0.06
    POSITIVE LOGITS
    vm
    0.07
    faq
    0.07
    ç«Ńè¯ļ
    0.07
    æĬķ稿éĤ®ç®±
    0.07
    æĺ¯éĤ£ä¹Ī
    0.07
    åħļè§Ħ
    0.07
    Speak
    0.07
    ä¸Ģæİ¢
    0.07
     Tow
    0.07
    ledge
    0.07
    Activations Density 0.000%

    No Known Activations