© 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. 65080
    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
    æĸ°åĬłåĿ¡
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    iab
    -0.07
    Ø©
    -0.07
    ÙĬØ¡
    -0.07
    ила
    -0.07
    ëĬĶ
    -0.07
    ity
    -0.07
    羣æŃ£æĪIJ为
    -0.07
    æĤį
    -0.07
    POSITIVE LOGITS
    ìį¨
    0.09
    è¿ĩçļĦ
    0.09
    äºĨä¸ĢåįĬ
    0.09
    çļĦæĺ¯
    0.08
    å¾Ĺå¾Ī
    0.08
    å¾ĹæĽ´
    0.08
    çļĦéĤ£æł·
    0.08
    åĪº
    0.08
    å¾Ĺ好
    0.08
    åĪ°çļĦ
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.