© 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. 7863
    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
    ÐłÐ¡
    -0.08
    _ENCODING
    -0.07
    ibold
    -0.07
    .eye
    -0.07
    åĪ«
    -0.07
    Inset
    -0.07
    wit
    -0.07
    ä¸įè¿ĺ
    -0.07
    å±ħæĺĵ
    -0.07
    æĪijçŁ¥éģĵ
    -0.07
    POSITIVE LOGITS
    åĩĨ
    0.08
    æĮĻ
    0.07
    éģ®
    0.07
     Manson
    0.07
    éĻĪè¿°
    0.06
    æĨ¬
    0.06
    ãģłãģĦ
    0.06
    ej
    0.06
    æĪ¿çļĦ
    0.06
    åĨµ
    0.06
    Activations Density 0.000%

    No Known Activations