© 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. 56513
    Prev
    Next
    INDEX
    Explanations

    medical conditions and research

    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
     Zimmerman
    -0.08
    éĤĤ
    -0.07
    illot
    -0.07
    ibr
    -0.06
    å¿
    -0.06
    大åŀĭçļĦ
    -0.06
    incer
    -0.06
    èĩªå·±è¢«
    -0.06
    é¢ĦæľŁçļĦ
    -0.06
     s
    -0.06
    POSITIVE LOGITS
    è¿Ļ个è¯Ŀé¢ĺ
    0.12
    åıĬ缸åħ³
    0.11
    åıĬåħ¶
    0.11
    -related
    0.10
    /topics
    0.10
     topic
    0.10
    è¯Ŀé¢ĺ
    0.10
     researching
    0.09
    åıĬåħ¶åºĶçĶ¨
    0.09
     research
    0.09
    Activations Density 0.578%

    No Known Activations