© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57077
    Prev
    Next
    INDEX
    Explanations

    knowingly or knew

    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
    æĹłæŀģ
    -0.07
    åĭ¤
    -0.06
    vements
    -0.06
     sinc
    -0.06
    æݢ索
    -0.06
    طا
    -0.06
    -columns
    -0.06
     Anspruch
    -0.06
    ä¸Ģæ¯Ķ
    -0.06
    èĩªåĬ¨
    -0.06
    POSITIVE LOGITS
    æĺİçŁ¥
    0.14
    ä¹ŁçŁ¥éģĵ
    0.11
    aware
    0.11
     aware
    0.11
     knowingly
    0.10
     awareness
    0.10
    å¾Īæ¸ħæ¥ļ
    0.10
    Aware
    0.10
    æĦıè¯ĨåĪ°
    0.09
    éĥ½çŁ¥éģĵ
    0.09
    Activations Density 0.052%

    No Known Activations