© 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. 32344
    Prev
    Next
    INDEX
    Explanations

    home or house

    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
    ä¿ĿåŃĺåľ¨
    -0.08
    æīĢå¤Ħ
    -0.08
    åĴĮåĬªåĬĽ
    -0.07
    ä½ĵçİ°åľ¨
    -0.07
    écr
    -0.07
    æīĢå¤ĦçļĦ
    -0.07
    åĩºçİ°åľ¨
    -0.07
    åĵªäºĽæĸ¹éĿ¢
    -0.07
    åıĪæĺ¯ä¸Ģå¹´
    -0.07
    кл
    -0.07
    POSITIVE LOGITS
    ä½ıçĿĢ
    0.10
    容纳
    0.09
    èĹıçĿĢ
    0.09
    æĶ¾ä¸įä¸ĭ
    0.08
    é«ĺå¯Ĩ
    0.08
     diisi
    0.08
    满äºĨ
    0.08
     Äijá»±ng
    0.08
     chứa
    0.07
    è£ħçĿĢ
    0.07
    Activations Density 0.367%

    No Known Activations