© 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. 15537
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terms

    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
    çļĦçī¹çĤ¹æĺ¯
    -0.07
     #:
    -0.07
    æĪij說
    -0.06
    çķ¿
    -0.06
    .configuration
    -0.06
    转载请注æĺİåĩºå¤Ħ
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
    æī¦
    -0.06
     whoever
    -0.06
    åħijçİ°
    -0.06
    POSITIVE LOGITS
    å°±çŁ¥éģĵäºĨ
    0.11
    åıªçŁ¥éģĵ
    0.11
    è¿ĻäºĽä¿¡æģ¯
    0.11
    ä¿¡æģ¯è¿Ľè¡Į
    0.11
    åį´ä¸įçŁ¥éģĵ
    0.10
    çŁ¥éģĵäºĨ
    0.10
    ä¹ŁçŁ¥éģĵ
    0.10
    çŁ¥æĻĵ
    0.09
     info
    0.09
     diketahui
    0.09
    Activations Density 0.078%

    No Known Activations