© 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. 47245
    Prev
    Next
    INDEX
    Explanations

    unicorn founders, degrowth, tanks

    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
    éĥ½åįģåĪĨ
    -0.08
    å¤įåĪ¶æĪĸ
    -0.08
    è¿Ļä¹Łæĺ¯
    -0.07
    æĿIJæĸĻåıĬ
    -0.07
    ovar
    -0.07
    âĤ¬.
    -0.07
    ä¹Łæĺ¯åįģåĪĨ
    -0.07
    mtree
    -0.07
    åĿĩ以
    -0.07
    ä¹ŁåįģåĪĨ
    -0.07
    POSITIVE LOGITS
    æľ¬èº«
    0.08
     itself
    0.08
     vs
    0.07
    æĺ¯åĶ¯ä¸Ģ
    0.07
    ä¹ĭäºİ
    0.07
     only
    0.07
     isn
    0.07
     bukanlah
    0.07
     demais
    0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    0.07
    Activations Density 0.307%

    No Known Activations