© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44620
    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
    Negative Logits
    èĬ±èIJ½
    -0.07
    常å§Ķ
    -0.06
    红äºĨ
    -0.06
    nev
    -0.06
    åĮºéķ¿
    -0.06
    ioc
    -0.06
    姬
    -0.06
    ä¼ĺç§ĢæķĻå¸Ī
    -0.06
     matches
    -0.06
    .uniform
    -0.06
    POSITIVE LOGITS
    LING
    0.09
    Unused
    0.09
    rodu
    0.09
    è¾ħåĬ©
    0.09
     Toro
    0.08
    edia
    0.08
     unused
    0.08
    _dummy
    0.08
    _unused
    0.08
    _SERIAL
    0.07
    Activations Density 0.000%

    No Known Activations