© 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. 64583
    Prev
    Next
    INDEX
    Explanations

    know given known

    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
    好äºĭ
    -0.07
    µ
    -0.07
    ertext
    -0.07
    erman
    -0.07
    äºĭäºĭ
    -0.06
    æł¹æľ¬æ²¡æľī
    -0.06
    igh
    -0.06
    éĿ¢ç§¯è¾¾
    -0.06
    icter
    -0.06
    ä¸ĢåĪĢ
    -0.06
    POSITIVE LOGITS
    çŁ¥åħ¶
    0.11
    çŁ¥éģĵ
    0.10
    åıªçŁ¥éģĵ
    0.09
    oded
    0.08
    çŁ¥éģĵä»ĸ
    0.08
    ä¹ŁçŁ¥éģĵ
    0.08
    åĴĮå¸ĮæľĽ
    0.08
    è¿ĻäºĽä¿¡æģ¯
    0.08
    çŁ¥éģĵä½ł
    0.07
    åį´ä¸įçŁ¥éģĵ
    0.07
    Activations Density 0.052%

    No Known Activations