© 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. 40064
    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
    仪
    -0.07
    Ùĥاب
    -0.07
    ats
    -0.07
    elling
    -0.06
    standing
    -0.06
     alternativ
    -0.06
     quals
    -0.06
    اخ
    -0.06
    els
    -0.06
    毡
    -0.06
    POSITIVE LOGITS
    lest
    0.08
    ZI
    0.08
    æĿİåŃIJ
    0.07
    vista
    0.07
    itus
    0.07
    hea
    0.07
    мп
    0.07
    endam
    0.07
    éĹ®é¢ĺ导åIJij
    0.07
    éĢļéĢļ
    0.07
    Activations Density 0.000%

    No Known Activations