© 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. 19138
    Prev
    Next
    INDEX
    Explanations

    , or . followed by clause

    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
    arcy
    -0.08
    æĢİä¹ĪåĬŀåij¢
    -0.07
     BUT
    -0.07
    루
    -0.07
    æīĢ以ä»ĸ
    -0.07
    pero
    -0.07
    ãģłãģĭãĤī
    -0.07
    ваÑĩ
    -0.07
    hut
    -0.07
    chage
    -0.07
    POSITIVE LOGITS
    以åıĬå¦Ĥä½ķ
    0.12
     indeed
    0.09
    以åıĬ
    0.08
    ç¡®å®ŀæĺ¯
    0.08
    以åıĬåľ¨
    0.08
    æīį好
    0.08
    以åıĬ缸åħ³
    0.08
    Indeed
    0.08
    èĢĮæĺ¯è¦ģ
    0.07
    æĢ§ä»¥åıĬ
    0.07
    Activations Density 0.121%

    No Known Activations