© 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. 23312
    Prev
    Next
    INDEX
    Explanations

    after comma

    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
     later
    -0.09
     ultimately
    -0.08
    åIJİæĿ¥çļĦ
    -0.08
     latter
    -0.07
    æľĢè¿ijåľ¨
    -0.07
    æľĢç»Ī
    -0.07
    æĻļå¹´
    -0.07
    åIJİç»Ń
    -0.07
    æľĢè¿ij
    -0.06
    åľ¨ä»¥åIJİ
    -0.06
    POSITIVE LOGITS
     ÙĪÙĤبÙĦ
    0.09
    .opensource
    0.09
    ä¸įä»ħæľī
    0.08
    ä¾ĿèĪĬ
    0.08
    ä¾ĿçĦ¶
    0.08
    DITION
    0.08
     angekommen
    0.08
    å¦ĤæŀľéģĩåĪ°
    0.08
    ãģ¾ãģ§ãģ®
    0.08
    ä¸įä½Ĩ
    0.08
    Activations Density 0.178%

    No Known Activations