© 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. 4302
    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
    udas
    -0.07
    æµij
    -0.07
    è¦ģ积æŀģ
    -0.07
    è´¡çĮ®
    -0.07
    çĪ±å²Ĺ
    -0.07
    owÄĻ
    -0.07
    临走
    -0.07
    é¡¹çĽ®åľ¨
    -0.07
    åįĥç§ĭ
    -0.06
    itou
    -0.06
    POSITIVE LOGITS
    .truth
    0.07
    çŁ
    0.07
    ç¡®
    0.07
    riz
    0.07
    æĮ¥
    0.07
    odash
    0.07
    æĭį
    0.07
    iant
    0.07
    Ŀ
    0.06
    rell
    0.06
    Activations Density 0.000%

    No Known Activations