© 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. 31798
    Prev
    Next
    INDEX
    Explanations

    announcements and dates

    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
    çĥŃéŨæĸĩç«ł
    -0.08
    isodes
    -0.07
    UEST
    -0.07
    åıįå¤įåıijä½ľ
    -0.07
    æľĢè¿ijåĩłå¹´
    -0.07
    zi
    -0.07
    strument
    -0.07
    colar
    -0.07
    åĩłå¹´æĿ¥
    -0.06
    дио
    -0.06
    POSITIVE LOGITS
     late
    0.09
     announce
    0.09
    Late
    0.09
    late
    0.09
    delay
    0.09
    åħ¬å¸ĥ
    0.09
     announcing
    0.08
    åħ¬å¸ĥçļĦ
    0.08
    宣å¸ĥäºĨ
    0.08
     announces
    0.08
    Activations Density 1.188%

    No Known Activations