© 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. 14952
    Prev
    Next
    INDEX
    Explanations

    news, history, problem, person

    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
     aforementioned
    -0.10
    éĢļè¿ĩ以ä¸Ĭ
    -0.10
    åīįè¿°
    -0.09
    对ä¸Ĭè¿°
    -0.09
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.08
     übrigens
    -0.08
    è¿Ŀåıįä¸Ĭè¿°
    -0.08
    çļĦè¿ĻäºĽ
    -0.08
    æįŁå¤±çļĦ
    -0.08
    并å¤Ħ
    -0.08
    POSITIVE LOGITS
    ãĨ
    0.07
    ｡
    0.06
    âĢIJ
    0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.06
     -
    0.06
    ï¿
    0.06
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.06
     —
    0.06
    æĨ¬
    0.06
    éĴ°
    0.06
    Activations Density 0.022%

    No Known Activations