© 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. 28284
    Prev
    Next
    INDEX
    Explanations

    since, it, we

    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
    åĽłä¸ºæĪij
    -0.12
    åĽłä¸ºæĪij们
    -0.11
    åĽłä¸ºæľīäºĨ
    -0.11
    åĽłä¸ºå¥¹
    -0.11
    åĽłä¸ºä»ĸ
    -0.11
    åĽłä¸ºä½ł
    -0.10
    åĽłæĤ¨çļĦ
    -0.10
    åĽłä¸ºæ²¡æľī
    -0.10
    åĽłä¸ºè¿ĻäºĽ
    -0.10
    åĽłä¸ºä»ĸ们
    -0.09
    POSITIVE LOGITS
    -called
    0.09
    forth
    0.08
     it
    0.08
    æĪij们åı¯ä»¥
    0.07
    we
    0.07
    ä¸Ķ
    0.07
    æľīå¿ħè¦ģ
    0.07
    ìļ°
    0.06
    ÃŃ
    0.06
     we
    0.06
    Activations Density 0.049%

    No Known Activations