© 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. 47267
    Prev
    Next
    INDEX
    Explanations

    proper noun names

    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
    -0.09
    ðŁ
    -0.07
     ðŁ
    -0.07
     ðŁij
    -0.07
    à¹īà¸Ńà¸Ļ
    -0.06
     ↵            ↵
    -0.06
    èģĮä¸ļåѦéĻ¢
    -0.06
    æ¸ħæ´ĹåīĤ
    -0.06
     **.**
    -0.06
     ↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.09
    æĤ¨åı¯èĥ½
    0.08
    ä¸Ĭä¸Ģ页
    0.08
    俱ä¹IJéĥ¨
    0.07
    lon
    0.07
    rawer
    0.07
    orde
    0.07
    ä¸ĢæĬ¹
    0.07
    注
    0.07
    oar
    0.07
    Activations Density 0.026%

    No Known Activations