© 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. 63328
    Prev
    Next
    INDEX
    Explanations

    newspaper 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
    å¤Ħéķ¿
    -0.08
    å°ĨçIJĥ
    -0.08
    å¾ĴåĪij
    -0.07
    ä¼ļéķ¿
    -0.06
    áºŃp
    -0.06
    æĹłåĬŁ
    -0.06
    çĥŃéŨæłĩçŃ¾
    -0.06
    è¿ĶåĽŀåĪĹ表
    -0.06
    ä»ĵ
    -0.06
    主任
    -0.06
    POSITIVE LOGITS
    æĬ¥
    0.10
    æĹ¥æĬ¥
    0.10
    daily
    0.10
    å½ĵ天çļĦ
    0.10
    æ¯ı天éĥ½æľī
    0.09
     newspaper
    0.09
    æ¯ı天çļĦ
    0.09
    Daily
    0.09
     daily
    0.09
     täg
    0.09
    Activations Density 0.379%

    No Known Activations