© 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. 18365
    Prev
    Next
    INDEX
    Explanations

    complex or complicated descriptions

    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
     trak
    -0.09
    å»ī
    -0.09
    kini
    -0.08
    æ²īå¯Ĥ
    -0.08
    çī¹åĪ«åĸľæ¬¢
    -0.08
    ÏĢÎŃ
    -0.08
    .ident
    -0.08
    èı
    -0.08
    epar
    -0.08
    izer
    -0.08
    POSITIVE LOGITS
    å¤įæĿĤçļĦ
    0.10
     complex
    0.09
    å¤įæĿĤ
    0.09
     complicated
    0.09
    complex
    0.08
    å¤įæĿĤæĢ§
    0.08
    æĽ²æĬĺ
    0.08
     irreg
    0.08
     indirect
    0.08
     irregular
    0.08
    Activations Density 0.221%

    No Known Activations