© 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. 42641
    Prev
    Next
    INDEX
    Explanations

    conversion to

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    åħ¬åı¸ä¸İ
    -0.08
    онеÑĢ
    -0.08
    æľ¬ç«ĻæīĢæľī
    -0.08
    liegen
    -0.07
    æĪĺçķ¥æĢ§æĸ°åħ´äº§ä¸ļ
    -0.07
    gewicht
    -0.07
    çĤ¹åĪ°
    -0.07
    _ORIGIN
    -0.07
    ุà¸ģ
    -0.07
    origin
    -0.07
    POSITIVE LOGITS
     via
    0.11
    çļĦè¿ĩç¨ĭä¸Ń
    0.10
    via
    0.09
    éĢĶä¸Ń
    0.09
    è¿Ļ个è¿ĩç¨ĭ
    0.09
    è¿Īè¿Ľ
    0.08
    çļĦè¿ĩç¨ĭ
    0.08
    è¿ĩç¨ĭä¸Ń
    0.08
    åĨįåĪ°
    0.08
     transition
    0.07
    Activations Density 0.193%

    No Known Activations