© 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. 48843
    Prev
    Next
    INDEX
    Explanations

    false statements and deception

    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
    ä¹īåĭĩ为
    -0.08
    å¼ķèµ·äºĨ
    -0.07
     caut
    -0.07
    ething
    -0.07
    çļĦå¿ĥæĥħ
    -0.07
    主æĶ»
    -0.07
     sighting
    -0.07
    ikä
    -0.07
    é¦Ļå±±
    -0.07
     NVIC
    -0.06
    POSITIVE LOGITS
    æĹłå¤Ħä¸įåľ¨
    0.09
    æĹłæŶæĹłåĪ»
    0.08
     ìŀijëıĻ
    0.07
    丧
    0.07
    GORITH
    0.07
    çĶļèĩ³è¿ŀ
    0.07
    精巧
    0.07
    åı¹
    0.07
     Everywhere
    0.07
     subtle
    0.07
    Activations Density 0.037%

    No Known Activations