© 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. 55675
    Prev
    Next
    INDEX
    Explanations

    discovery of self

    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
    人åij½
    -0.08
    æ¯ıçıŃ
    -0.08
    åѦçĶŁçļĦåŃ¦ä¹łåħ´è¶£
    -0.07
     гÑĢоз
    -0.07
    gue
    -0.07
    enov
    -0.07
    大æ±ī
    -0.07
     terminated
    -0.07
    tlement
    -0.07
    abort
    -0.07
    POSITIVE LOGITS
     lifelong
    0.09
    åĽłäººèĢĮå¼Ĥ
    0.09
    个ä½ĵ
    0.08
    对个人
    0.08
    个ä½ĵçļĦ
    0.08
     procrast
    0.08
    éĢĤ度çļĦ
    0.08
     Oprah
    0.08
     personal
    0.08
    ä¸İä»ĸ人
    0.08
    Activations Density 0.109%

    No Known Activations