© 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. 27040
    Prev
    Next
    INDEX
    Explanations

    quotation marks or apostrophes

    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
    áĢ±áĢ¸
    -0.06
    æį®æѤ
    -0.06
    عÙĨ
    -0.06
    好æĦŁ
    -0.06
    ourke
    -0.06
    æį·
    -0.06
    _wr
    -0.06
    /operator
    -0.06
    æѤ
    -0.06
     fois
    -0.06
    POSITIVE LOGITS
    ãĢģ“
    0.10
     yani
    0.09
    пев
    0.08
    äºĮåŃĹ
    0.08
    æĹłéĹ»
    0.08
    åĬłåħ³æ³¨
    0.08
    ä½ķå¿ħ
    0.08
    ä¸įæį¢
    0.08
    ÙĪدÙĬØ©
    0.08
    ä¸į稳
    0.08
    Activations Density 0.016%

    No Known Activations