© 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. 38292
    Prev
    Next
    INDEX
    Explanations

    Link Party or blog closing

    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
    éĢļ宵
    -0.07
    (?)
    -0.07
    ég
    -0.06
    åľ¨çĽ®åīį
    -0.06
    æĸ¹éĴĪ
    -0.06
    ingu
    -0.06
    å´©åĿı
    -0.06
    åľ¨æ¯ĶèµĽ
    -0.06
    lew
    -0.06
     memakan
    -0.06
    POSITIVE LOGITS
    çĶŁåij½ä¸ŃçļĦ
    0.08
    人çĶŁ
    0.08
    å¿ĥå®ī
    0.08
    大åįĥ
    0.07
    èĢĮä»Ĭ
    0.07
    çĶŁåij½ä¸Ń
    0.07
    hdr
    0.07
    eeper
    0.07
    keepers
    0.07
    ä¾µ
    0.07
    Activations Density 0.005%

    No Known Activations