© 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. 9654
    Prev
    Next
    INDEX
    Explanations

    invisible stories

    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
    åĵ½
    -0.08
    æľīä¸į
    -0.07
    对幼åĦ¿
    -0.07
    æѤ类
    -0.07
    缸åºĶçļĦ
    -0.07
    æľīç»ıéªĮ
    -0.07
    伪
    -0.07
    åľ°ä¹ħ
    -0.07
    缮çŀª
    -0.07
    æĢĶ
    -0.07
    POSITIVE LOGITS
     invisible
    0.09
     whispers
    0.08
     tells
    0.08
    invisible
    0.07
     tomorrow
    0.07
     cosmic
    0.07
    æĺ¯ä¸įæĺ¯å¾Ī
    0.07
     stories
    0.07
    åı¯èĥ½å°±
    0.07
     Invisible
    0.07
    Activations Density 0.181%

    No Known Activations