© 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. 55580
    Prev
    Next
    INDEX
    Explanations

    secondary disguise

    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
    èĢĮéĿŀ
    -0.10
    èĢĮä¸įæĺ¯
    -0.10
     rather
    -0.08
    ä¸įåIJĮäºİ
    -0.08
    rather
    -0.08
    æ¯ĶæĻ®éĢļ
    -0.08
    æ¯Ķèµ·
    -0.07
    å°±ä¼ļåıijçİ°
    -0.07
    缸æ¯Ķäºİ
    -0.07
     piuttosto
    -0.07
    POSITIVE LOGITS
    åı¦è¡Į
    0.09
    çŃīåħ¶ä»ĸ
    0.08
    åı¦æľī
    0.08
     thereafter
    0.07
     afterward
    0.07
     comparatively
    0.07
    顯
    0.07
     theirs
    0.07
     ikut
    0.07
    ä¸İä¹ĭ
    0.06
    Activations Density 0.114%

    No Known Activations