© 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. 27493
    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
    åĭĩå¾Ģ缴åīį
    -0.07
    foort
    -0.07
    æľĿæ°Ķ
    -0.07
    åIJĮèĪŁ
    -0.07
    èĤ²æīį
    -0.07
    è¹
    -0.06
    åĸĭ
    -0.06
    urally
    -0.06
    ä½ĻçĥŃ
    -0.06
    人åķĬ
    -0.06
    POSITIVE LOGITS
    æĭĨ
    0.08
    æĪĸ缴æİ¥
    0.07
    PrototypeOf
    0.07
    å°Ķå¾·
    0.07
    à¦ķà§įষà§ĩ
    0.07
    缮å®ī
    0.07
    CLR
    0.07
    নà§įত
    0.07
    æĴ¤
    0.06
    usine
    0.06
    Activations Density 0.000%

    No Known Activations