© 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. 49165
    Prev
    Next
    INDEX
    Explanations

    if you will

    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
    è¦ģä¹Īæĺ¯
    -0.09
     zwar
    -0.08
    è¦ģä¹Ī
    -0.08
    issé
    -0.07
     infatti
    -0.07
    åįĥå±±
    -0.07
    åİŁæĺ¯
    -0.07
     ugyanis
    -0.07
    ushman
    -0.07
    è¿ĺæĺ¯éľĢè¦ģ
    -0.07
    POSITIVE LOGITS
    åIJİèĢħ
    0.10
     latter
    0.09
     afterward
    0.08
    没éĤ£ä¹Ī
    0.07
    æķ£
    0.07
    æĢ»ä¹ĭ
    0.07
    äºĮèĢħ
    0.07
    EMP
    0.06
    æĭIJ
    0.06
    ÃŃstica
    0.06
    Activations Density 0.314%

    No Known Activations