© 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. 27746
    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
    uxtap
    -0.08
    łĢ
    -0.07
    طاÙĤ
    -0.07
    äºŃäºŃ
    -0.07
    Ìģ
    -0.07
    ov
    -0.07
    éģ¿åŃķèį¯
    -0.06
    schap
    -0.06
    ITTER
    -0.06
    r
    -0.06
    POSITIVE LOGITS
    æĿĢçļĦ
    0.08
    串
    0.08
    ë°Ķë¡ľ
    0.07
    èĶ¬
    0.07
    leih
    0.07
    -carousel
    0.07
    heil
    0.07
    ieben
    0.07
    åħ¢
    0.07
    çľĭåĩº
    0.06
    Activations Density 0.000%

    No Known Activations