© 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. 7499
    Prev
    Next
    INDEX
    Explanations

    world record

    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
    ispens
    -0.07
    åĩºäºĨéĹ®é¢ĺ
    -0.07
    åIJģ
    -0.07
    anaf
    -0.07
    BITS
    -0.07
    éĩijå¸ģ
    -0.07
    æĦ
    -0.07
     Sabb
    -0.07
     <<<
    -0.07
    å¾·åŁº
    -0.07
    POSITIVE LOGITS
    纪å½ķ
    0.12
     record
    0.10
    è®°å½ķçļĦ
    0.10
     rekord
    0.10
     ÑĢекоÑĢ
    0.10
    record
    0.09
     기ë¡Ŀ
    0.09
     records
    0.09
     Guinness
    0.09
     recorded
    0.09
    Activations Density 0.325%

    No Known Activations