© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57008
    Prev
    Next
    INDEX
    Explanations

    adage or maxim

    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
    ãĥ¼ãĤ¹
    -0.08
    طار
    -0.08
    æĶ¾ä¸Ĭ
    -0.07
    ÑĤиÑĩеÑģки
    -0.07
    aç
    -0.07
    uç
    -0.07
    æĵįä½ľä¸Ĭ
    -0.07
    æĸĽ
    -0.07
    éħįä¸Ĭ
    -0.07
     typeof
    -0.07
    POSITIVE LOGITS
    ä»¥äººä¸ºæľ¬
    0.09
    å±ŀåľ°
    0.08
    çļĨæľī
    0.08
    å¹³çŃīçļĦ
    0.08
    åģļäºĭæĥħ
    0.07
    åĺĽ
    0.07
    å°Ĭéĩį
    0.07
    ory
    0.07
    çļĦé«ĺ度éĩįè§Ĩ
    0.07
    è¦ģæľī
    0.07
    Activations Density 0.082%

    No Known Activations