© 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. 56661
    Prev
    Next
    INDEX
    Explanations

    articles and descriptions

    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°±æĺ¯è¿Ļä¹Ī
    -0.08
    alfa
    -0.08
    ajak
    -0.07
    ardi
    -0.07
    rio
    -0.07
     verge
    -0.07
    ä½ķçŃī
    -0.07
    abu
    -0.07
    æľī太å¤ļ
    -0.07
    å¥ĩè§Ĥ
    -0.07
    POSITIVE LOGITS
    \"
    0.08
    pone
    0.08
     \"
    0.08
    并ä¸Ķ
    0.07
    åIJĥèµ·æĿ¥
    0.07
    ä½Ĩåį´
    0.06
    ä¸įå±ŀäºİ
    0.06
    çļĦè¯Ħä»·æĺ¯
    0.06
    .jsx
    0.06
    çĶ¨æĿ¥
    0.06
    Activations Density 0.077%

    No Known Activations