© 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. 19150
    Prev
    Next
    INDEX
    Explanations

    indicate reservations or questions

    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
    åľ¨åŃ¦ä¹łä¸Ń
    -0.09
    çļĦè¿Ļä¸Ģ
    -0.08
    ulte
    -0.08
    undry
    -0.08
    quilla
    -0.08
    è¿Ļç§įæĦŁè§ī
    -0.08
    ẩy
    -0.08
    çŃīåħ¶ä»ĸ
    -0.07
    ä¼łç»Łäº§ä¸ļ
    -0.07
    usher
    -0.07
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.08
     therein
    0.07
     dabei
    0.07
     darin
    0.07
    ç»İ
    0.07
    avez
    0.06
    ave
    0.06
    غÙĪ
    0.06
     Friends
    0.06
    avig
    0.06
    Activations Density 0.551%

    No Known Activations