© 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. 34390
    Prev
    Next
    INDEX
    Explanations

    complex variation varies

    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
     allerdings
    -0.09
    berman
    -0.08
     drawback
    -0.08
    注æĦıçļĦæĺ¯
    -0.08
     Fisc
    -0.08
     пÑĢавда
    -0.08
    anded
    -0.08
     toutefois
    -0.08
    ç±»åŀĭ为
    -0.07
    aptor
    -0.07
    POSITIVE LOGITS
     complex
    0.11
    å¤įæĿĤçļĦ
    0.11
    ä¹Łä¸įçŁ¥éģĵ
    0.10
    å¤įæĿĤ
    0.10
    çŀ¬æģ¯
    0.09
    complex
    0.09
    æīįèĥ½çľŁæŃ£
    0.09
    å®Įåħ¨ä¸įåIJĮçļĦ
    0.09
    æľªçŁ¥çļĦ
    0.09
    Complex
    0.09
    Activations Density 0.121%

    No Known Activations