© 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. 50540
    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
    uage
    -0.08
    æĶ¾åľ¨ç¬¬ä¸Ģä½į
    -0.06
     nex
    -0.06
    åĪ°åºķæľīå¤ļ
    -0.06
    å±ĪæĮĩ
    -0.06
    vist
    -0.06
    麹
    -0.06
    就好
    -0.06
    cott
    -0.06
    efa
    -0.06
    POSITIVE LOGITS
    Ĭ
    0.08
    بس
    0.07
    éĽĦ
    0.07
    jeta
    0.07
    Ú¾ÛĮ
    0.07
     materia
    0.07
    æļ´é£İ
    0.07
    ould
    0.07
    Modified
    0.07
    éĽĮ
    0.06
    Activations Density 0.000%

    No Known Activations