© 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. 42860
    Prev
    Next
    INDEX
    Explanations

    artificial or fictional

    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
    áĢ²
    -0.07
    ÛĮØ´
    -0.07
    çĥŃçĤ¹éĹ®é¢ĺ
    -0.07
    èĩªçĦ¶æĺ¯
    -0.07
    ç»Ŀä¸įæĺ¯
    -0.07
    bane
    -0.07
    éģĵè¿ľ
    -0.07
    icona
    -0.07
    主åŃIJ
    -0.07
    æľīä¸Ń
    -0.06
    POSITIVE LOGITS
    人为
    0.12
     artificially
    0.12
     artificial
    0.10
     fictional
    0.09
    人工
    0.09
     Artificial
    0.09
    èĻļæŀĦ
    0.08
    fiction
    0.08
     hypothetical
    0.08
    åıįæŃ£
    0.08
    Activations Density 0.043%

    No Known Activations