© 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. 49125
    Prev
    Next
    INDEX
    Explanations

    his or her

    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
    Ø©
    -0.14
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    翼翼
    -0.08
    tte
    -0.08
    ï¸ı
    -0.08
    chnik
    -0.08
    à¸ģารà¸ĵà¹Į
    -0.07
     हà¥ģà¤Ī
    -0.07
    çļĦé¦ĸè¦ģ
    -0.07
    ainties
    -0.07
    POSITIVE LOGITS
    /her
    0.24
    /she
    0.24
    zelf
    0.17
     himself
    0.16
    èĢģ人家
    0.11
    -même
    0.11
     Himself
    0.11
    zelfde
    0.10
    ä¿©
    0.10
    brew
    0.10
    Activations Density 0.246%

    No Known Activations