© 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. 22456
    Prev
    Next
    INDEX
    Explanations

    list following my

    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
    æ²®
    -0.06
     rendez
    -0.06
     Raq
    -0.06
    å¦ĤæĦı
    -0.06
    å®ŀå¿ĥ
    -0.06
    æķ£å¸ĥ
    -0.06
    ï¾ŀ
    -0.06
    åĢ¼çļĦ
    -0.06
    æī£
    -0.06
    çĦ¶æĺ¯
    -0.06
    POSITIVE LOGITS
    缮æłĩåĴĮ
    0.08
    رÙĪض
    0.08
    ä»»åĬ¡åĴĮ
    0.08
    第ä¸Ģè½®
    0.08
    åħĪçĥĪ
    0.08
    imit
    0.08
    ä¸Ĭä¸ĭæĸĩ
    0.07
    áī½
    0.07
    åĴĮæĪijçļĦ
    0.07
    {text
    0.07
    Activations Density 0.010%

    No Known Activations