© 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. 62107
    Prev
    Next
    INDEX
    Explanations

    critical medical conditions

    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
    çijķçĸµ
    -0.08
    å®ļæľŁå¯¹
    -0.08
     annoyance
    -0.08
     Anno
    -0.08
    æ½ľç§»é»ĺåĮĸ
    -0.07
    ä¹ħèĢĮä¹ħä¹ĭ
    -0.07
     пÑĢоÑĤивоÑĢе
    -0.07
    çĹĴ
    -0.07
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    -0.07
    aiser
    -0.07
    POSITIVE LOGITS
    æĬ¢æķij
    0.15
    ä¼ijåħĭ
    0.13
    åį±æĢ¥
    0.12
     emergency
    0.12
    ç´§æĢ¥
    0.11
    æĢ¥
    0.11
    æĢ¥æķij
    0.11
    çĶŁæŃ»
    0.11
    æķijæ²»
    0.10
    ç´§æĢ¥æĥħåĨµ
    0.10
    Activations Density 0.362%

    No Known Activations