© 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. 27265
    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
    æĺ¯ç»ı
    -0.08
    çĶŁæ´»åľĪ
    -0.07
     ìĸ¸
    -0.06
    fon
    -0.06
    æīĵè¿ĩ
    -0.06
    ERE
    -0.06
    .sd
    -0.06
    è¦ģéĹ»
    -0.06
    æļĤè¡Į
    -0.06
    ×Ļ×IJ
    -0.06
    POSITIVE LOGITS
    åĴĮå¤ĸ
    0.07
    itat
    0.07
    ÑĤаж
    0.07
    -path
    0.07
    tega
    0.07
    é¾IJ
    0.06
    omat
    0.06
    rotch
    0.06
    ainless
    0.06
    ayaan
    0.06
    Activations Density 0.000%

    No Known Activations