© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27026
    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
    umen
    -0.08
    teau
    -0.08
    erview
    -0.08
    å®Ŀé¾Ļ
    -0.08
    代åĬŀ
    -0.08
    loch
    -0.08
    antro
    -0.08
    à¸Ħาย
    -0.07
    .viewport
    -0.07
     ruá»Ļt
    -0.07
    POSITIVE LOGITS
    çıĪ
    0.06
    åľ¨ç¬¬
    0.06
    æĵĴ
    0.06
    踵
    0.06
    æĻĸ
    0.06
    caya
    0.06
    è®¤çľŁåģļ好
    0.06
    è½¬åŁºåĽł
    0.06
    谨记
    0.06
    æīĵè¿ĩ
    0.05
    Activations Density 0.000%

    No Known Activations