© 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. 16466
    Prev
    Next
    INDEX
    Explanations

    formulæ, conditions, and expressions

    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
    å°Ķé¡¿
    -0.07
    (named
    -0.07
    åħĭåĬĽ
    -0.07
    èĩªåĪ¶
    -0.07
    åĶ·
    -0.06
    utton
    -0.06
    åħ¨ç¨ĭ
    -0.06
    uncul
    -0.06
     Biz
    -0.06
    è§Ĩç½ij
    -0.06
    POSITIVE LOGITS
    åı¯å¾ª
    0.08
     relating
    0.07
    çªįéŨ
    0.07
    autre
    0.07
     resembling
    0.07
    åıij表æĪĸ
    0.07
    æĿ¥è¡¨è¾¾
    0.07
    类似äºİ
    0.07
    omething
    0.07
    æĺ¯ä»Ģä¹Īåij¢
    0.07
    Activations Density 0.147%

    No Known Activations