© 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. 25483
    Prev
    Next
    INDEX
    Explanations

    male pronouns and 'boy'

    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
     herself
    -0.16
    å«ģç»Ļ
    -0.13
    åĩºå«ģ
    -0.12
     ÙĨÙģسÙĩا
    -0.12
    她èĩªå·±
    -0.12
    她们çļĦ
    -0.11
    æ¯į女
    -0.11
    她们
    -0.11
    å¨ĺ家
    -0.10
    éĹº
    -0.10
    POSITIVE LOGITS
     himself
    0.20
    娶
    0.15
     Himself
    0.14
    /she
    0.13
    èĭ±ä¿Ĭ
    0.13
    å¸ħæ°Ķ
    0.13
    çĿ¾ä¸¸
    0.12
    çĪ¶åŃIJ
    0.11
     masculinity
    0.11
    åĮħçļ®
    0.11
    Activations Density 0.928%

    No Known Activations