© 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. 38506
    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
    åŀ«
    -0.08
    æ´»
    -0.08
    äºĴ
    -0.07
     Apel
    -0.07
     gul
    -0.07
    èIJ½åı¶
    -0.06
     ess
    -0.06
    inkel
    -0.06
    çħĮ
    -0.06
    Ùģر
    -0.06
    POSITIVE LOGITS
    _ALIGNMENT
    0.08
    пно
    0.07
    aub
    0.07
    åIJī祥å¦ĤæĦı
    0.07
    æľīæĿĥä¿ĿçķĻ
    0.07
    utc
    0.07
    æĶ¯éħįæĶ¶åħ¥
    0.07
    å§Ķä»»
    0.06
    egg
    0.06
    azi
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.