© 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. 11303
    Prev
    Next
    INDEX
    Explanations

    related 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
    丽
    -0.07
    allen
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    对äºİä¸ĢäºĽ
    -0.06
    мони
    -0.06
    大éĥ¨åĪĨçļĦ
    -0.06
    åħ¶ä»ĸåľ°æĸ¹
    -0.06
     seines
    -0.06
    éºĹ
    -0.06
    ritte
    -0.06
    POSITIVE LOGITS
     Unblock
    0.07
    ianas
    0.07
    åIJĮä¸Ģ个
    0.07
    æĸĩç«łæłĩçŃ¾
    0.07
     alike
    0.07
    /about
    0.06
     данномÑĥ
    0.06
    ibraries
    0.06
    ivas
    0.06
    ionales
    0.06
    Activations Density 0.041%

    No Known Activations