© 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. 18470
    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
     competition
    -0.08
    ׳×ķת
    -0.07
    anze
    -0.07
     Wett
    -0.07
    æĦŁåıĹçĿĢ
    -0.07
     "\""
    -0.07
     mondial
    -0.07
    æľī天
    -0.07
    Ñİд
    -0.07
    èĢĥèĻijçļĦ
    -0.07
    POSITIVE LOGITS
    è¡Į
    0.07
    ISA
    0.07
    ån
    0.07
    olan
    0.06
    ä»İè¿ĻéĩĮ
    0.06
    วà¸Ļ
    0.06
    kah
    0.06
    åĴĮç»Ħç»ĩ
    0.06
     pel
    0.06
    åĩŃ
    0.06
    Activations Density 0.000%

    No Known Activations