© 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. 29200
    Prev
    Next
    INDEX
    Explanations

    conditional statements or logic

    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
    asca
    -0.08
    åĮ»éĻ¢åľ°åĿĢ
    -0.08
    igram
    -0.07
    owitz
    -0.07
    rip
    -0.07
    æĻļæĬ¥
    -0.07
    æĺłåĥı
    -0.07
    Enumerable
    -0.07
    ovich
    -0.07
    åħ¶æŀĹ
    -0.07
    POSITIVE LOGITS
    æł¹æį®ä¸įåIJĮ
    0.14
    åºĶæł¹æį®
    0.14
     depending
    0.13
    éľĢè¦ģæł¹æį®
    0.13
    conditional
    0.12
     varying
    0.12
    éĴĪ对ä¸įåIJĮ
    0.12
    åĮºåĪĨ
    0.12
     conditional
    0.12
    depending
    0.12
    Activations Density 0.784%

    No Known Activations