© 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. 37910
    Prev
    Next
    INDEX
    Explanations

    mapping

    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
    imal
    -0.07
    를
    -0.07
    пи
    -0.06
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.06
    ت
    -0.06
    æľī
    -0.06
    åĴĮæĪijçļĦ
    -0.06
    borough
    -0.06
    åĴĮä¸Ģ个
    -0.06
    çıŃ
    -0.06
    POSITIVE LOGITS
    çļĦ人åĴĮ
    0.12
    çļĦä¸ĢåĪĩéĥ½
    0.11
    çļĦä¸ĢåĪĩ
    0.10
    å°½æĺ¯
    0.10
    çļĦ人æ°Ķ
    0.10
    çļĦ人类
    0.10
    ãģ§ãģ®
    0.10
    çļĦä¸ĢäºĽ
    0.09
    åĽ¾åĪĨç±»åı·
    0.09
     olev
    0.09
    Activations Density 0.003%

    No Known Activations