© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14048
    Prev
    Next
    INDEX
    Explanations

    code definitions and structure

    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
    errat
    -0.07
    iro
    -0.07
     dur
    -0.06
    bon
    -0.06
    Äĩi
    -0.06
     ro
    -0.06
     decent
    -0.06
    å¾·éĺ³
    -0.06
    rg
    -0.06
    çݯå¢ĥä¿ĿæĬ¤
    -0.06
    POSITIVE LOGITS
    å¦Ĥæŀľæĺ¯
    0.09
    ÙĪØ´
    0.08
    å¦Ĥæŀľåıªæĺ¯
    0.08
    ADM
    0.07
    .construct
    0.07
    å¼Ģå¼ł
    0.07
    æīĢåIJij
    0.07
    -marker
    0.07
    æįĨ
    0.07
     instead
    0.07
    Activations Density 0.121%

    No Known Activations