© 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. 20584
    Prev
    Next
    INDEX
    Explanations

    respectively followed by verbs

    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
    继ç»Ńéĺħ读
    -0.10
    sait
    -0.09
    upu
    -0.09
    raul
    -0.09
    Reached
    -0.09
    elig
    -0.09
    販
    -0.09
    ä¸įå¾ĹäºĨ
    -0.09
    å¹´çļĦæŶåĢĻ
    -0.09
    Ø£ÙĥÙħÙĦ
    -0.09
    POSITIVE LOGITS
    æī¬æī¬
    0.09
    nya
    0.09
    اÙĭ
    0.09
    ãģĺãĤģ
    0.08
    ric
    0.08
    å¼ĢæĿ¥
    0.07
    åĴĮ
    0.07
    ì§Ģìĸ´
    0.07
    ouncer
    0.07
    ãĢħãģ«
    0.07
    Activations Density 0.001%

    No Known Activations