© 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. 50531
    Prev
    Next
    INDEX
    Explanations

    additional explanation introducing clauses

    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
    Cls
    -0.07
     Plast
    -0.07
    ffect
    -0.07
    èĩ³äºİ
    -0.07
    次äºİ
    -0.07
    à¸ģา
    -0.07
    zel
    -0.07
    ystone
    -0.07
    atis
    -0.07
    actly
    -0.07
    POSITIVE LOGITS
    æľ¬å°±æĺ¯
    0.11
     sheer
    0.10
    æľ¬èº«å°±æĺ¯
    0.09
    ãģĿãĤĤãģĿãĤĤ
    0.09
    æľ¬èº«çļĦ
    0.09
    æľ¬èº«
    0.08
    æľ¬æĿ¥å°±æĺ¯
    0.08
    æľ¬æĿ¥å°±
    0.08
     anyway
    0.08
    æľ¬èº«å°±
    0.07
    Activations Density 0.222%

    No Known Activations