© 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. 25697
    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
    ovi
    -0.07
    ãĤ®ãĥ¥
    -0.07
    strap
    -0.07
    çºĸ
    -0.07
    undi
    -0.07
     Refuge
    -0.07
    γκα
    -0.07
     Funny
    -0.07
    icot
    -0.07
    æĿ¥äºº
    -0.07
    POSITIVE LOGITS
    æĢĿ
    0.07
    ivor
    0.06
    ä½ľçŃĶ
    0.06
     ná»ķ
    0.06
    åģ¥åĦ¿
    0.06
    fu
    0.06
    ä¸įçķĻ
    0.06
    å¹³
    0.06
    /runtime
    0.06
    åĪ
    0.06
    Activations Density 0.000%

    No Known Activations