© 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. 30527
    Prev
    Next
    INDEX
    Explanations

    example, demonstration, counterexample

    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¸ĢèĤ¡
    -0.08
    pon
    -0.08
    жней
    -0.08
    æŃ£ä¸Ń
    -0.07
    çŃīåIJĦ项
    -0.06
    chemas
    -0.06
    ule
    -0.06
    åĴĮä¸ĭ
    -0.06
    roma
    -0.06
    åĨ³å®ļçļĦ
    -0.06
    POSITIVE LOGITS
    çļĦä¾ĭåŃIJ
    0.10
     contohnya
    0.10
    ä¾ĭåŃIJ
    0.09
    æŀĦéĢł
    0.09
     examples
    0.09
     пÑĢимеÑĢ
    0.08
     contoh
    0.08
     example
    0.08
    æī¾ä¸Ģ个
    0.08
     demonstration
    0.08
    Activations Density 0.036%

    No Known Activations