© 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. 24751
    Prev
    Next
    INDEX
    Explanations

    incidents causing death or injury

    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
    éĢIJå¹´
    -0.07
    çģ¾
    -0.07
     every
    -0.07
    åħ¨è·¯æ®µ
    -0.06
    æ¯ıä¸ĢæĿ¡
    -0.06
    éĿŀåħ¸
    -0.06
     boycott
    -0.06
    æ¯ıä¸Ģ
    -0.06
    æ¯ıä¸Ģç§į
    -0.06
    çĹħèĻ«å®³
    -0.06
    POSITIVE LOGITS
    çĸijä¼¼
    0.10
     reportedly
    0.10
     diduga
    0.10
     suspected
    0.10
    æĹ¥åĩĮæĻ¨
    0.09
    istory
    0.09
    éĵ¶å±±
    0.09
    å½ĵ天ä¸ĭåįĪ
    0.09
    è¿Ļèµ·
    0.09
    å¤ļåIJį
    0.09
    Activations Density 0.779%

    No Known Activations