© 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. 1118
    Prev
    Next
    INDEX
    Explanations

    proven by, follow, move, quick, areas, use, entire, output

    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
     übrigens
    -0.12
    éĢļè¿ĩ以ä¸Ĭ
    -0.10
    icals
    -0.08
    ä¹ŁæĽ´åĬł
    -0.08
    weiler
    -0.08
     infine
    -0.08
    åıĹ伤çļĦ
    -0.08
    伤çļĦ
    -0.07
    æĥħåĨµåıĬ
    -0.07
    enal
    -0.07
    POSITIVE LOGITS
     ↵
    0.08
    č↵
    0.08
    çĵ
    0.06
    âĢIJ
    0.06
     č↵
    0.06
    <br
    0.06
    çļĭ
    0.06
    çݺ
    0.06
      ↵
    0.06
    0.06
    Activations Density 0.083%

    No Known Activations