© 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. 39011
    Prev
    Next
    INDEX
    Explanations

    system structure or plan

    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
    ationally
    -0.08
    梱
    -0.08
     phép
    -0.08
    åĩ¡äºĭ
    -0.07
    ä¸ĢæĮĩ
    -0.07
    åĩŃåĢŁåħ¶
    -0.07
    ingati
    -0.07
    èĢĮèĩ³
    -0.07
    æİ¥åĪ°äºĨ
    -0.07
    å¦Ĥåħ¶
    -0.07
    POSITIVE LOGITS
    æĺ¯æĢİæł·çļĦ
    0.10
    æĺ¯è¿Ļæł·çļĦ
    0.09
    å¦Ĥä¸ĭ
    0.08
    çļĦä¸ĢåĪĩéĥ½
    0.08
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.08
    å¦Ĥä¸ĭåĽ¾
    0.07
    ä¸Ńæľī
    0.07
     consists
    0.07
     resembles
    0.07
    类似äºİ
    0.07
    Activations Density 0.026%

    No Known Activations