© 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. 31514
    Prev
    Next
    INDEX
    Explanations

    racemic mixture

    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
    ä¸İ设计
    -0.07
    身
    -0.07
    æ
    -0.07
    _wr
    -0.07
    .rnn
    -0.07
    æµģ
    -0.07
    è¾ŀ
    -0.06
    ä¸İæľįåĬ¡
    -0.06
     convo
    -0.06
    æĪĪ
    -0.06
    POSITIVE LOGITS
     mixture
    0.09
    æ··åIJĪçī©
    0.09
    ä¸įçŁ¥ä¸įè§īä¸Ń
    0.08
    æĪĸéĥ¨åĪĨ
    0.08
    æĹłæīĢè°ĵ
    0.08
    neutral
    0.08
    æIJĵ
    0.08
    ä¸ŃæĢ§
    0.07
    YRO
    0.07
     comprised
    0.07
    Activations Density 0.004%

    No Known Activations