© 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. 14333
    Prev
    Next
    INDEX
    Explanations

    according to their

    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
    好çļĦ产åĵģ
    -0.08
    å¤Ħå¤Ħ
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    ekor
    -0.08
    onti
    -0.08
    fds
    -0.07
    umer
    -0.07
    èĢ³çĽ®
    -0.07
    äºĭäºĭ
    -0.07
     Structures
    -0.07
    POSITIVE LOGITS
     their
    0.11
    åIJĦèĩªçļĦ
    0.10
    their
    0.09
    åIJĦèĩª
    0.08
    æľīæĹł
    0.08
    å®ĥ们çļĦ
    0.08
     иÑħ
    0.08
    æīĢå±ŀ
    0.07
     Their
    0.07
    以ä¸ĭæĸ¹å¼ı
    0.07
    Activations Density 0.114%

    No Known Activations