© 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. 48537
    Prev
    Next
    INDEX
    Explanations

    `world filled`, `user`, `Mock`, `Core`, `JB`

    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
    umpt
    -0.07
    çĽ¸å¯¹ç¨³å®ļ
    -0.07
    庸
    -0.07
    asse
    -0.07
    ä¼ĺ
    -0.07
     Cutter
    -0.07
    å©´
    -0.07
    ç«ĭ
    -0.07
    enschaft
    -0.06
    orden
    -0.06
    POSITIVE LOGITS
    çĸij
    0.07
    æ¡ĤåĽŃ
    0.07
    ÃŃce
    0.07
    æ°´åľŁä¿ĿæĮģ
    0.07
    çļĦ幸ç¦ı
    0.07
    ä¸įæĶ¾
    0.06
    åĪĨåĪ«ä¸º
    0.06
    Cb
    0.06
     @{
    0.06
    lili
    0.06
    Activations Density 0.002%

    No Known Activations