© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    ribosomes

    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
    æ¢ħæŀĹ
    -0.08
    ctr
    -0.07
    ilet
    -0.07
    西éŨ
    -0.07
    etra
    -0.06
    Ïģκ
    -0.06
    ihil
    -0.06
    èĮģ
    -0.06
    loops
    -0.06
    ç£ķ
    -0.06
    POSITIVE LOGITS
    çŁ¥è¯ĨçĤ¹
    0.10
    çļĦçī¹çĤ¹
    0.09
    çļĦ缸åħ³çŁ¥è¯Ĩ
    0.08
    å¿ħçŃĶ
    0.08
     characteristics
    0.08
    ä¼ĺ缺çĤ¹
    0.08
    çī¹çĤ¹
    0.08
     Characteristics
    0.08
    åĴĮçī¹çĤ¹
    0.08
    çī¹çĤ¹åĴĮ
    0.07
    Activations Density 0.038%

    No Known Activations