© 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. 47944
    Prev
    Next
    INDEX
    Explanations

    patients treated

    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
     itself
    -0.10
    und
    -0.07
    åĴĮè´¨éĩı
    -0.06
    ikh
    -0.06
    对人çļĦ
    -0.06
    สำหรัà¸ļà¸ľà¸¹à¹ī
    -0.06
    j
    -0.06
    æľ¬èº«
    -0.06
    åľ¨åѦçĶŁ
    -0.06
    wal
    -0.06
    POSITIVE LOGITS
     who
    0.11
    schaften
    0.11
    à¬ĻàŃįà¬ķ
    0.10
     اÙĦØ°ÙĬÙĨ
    0.10
     whose
    0.09
    们çļĦ
    0.09
    Innen
    0.09
    whose
    0.09
    innen
    0.09
     whom
    0.09
    Activations Density 0.669%

    No Known Activations