© 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. 30955
    Prev
    Next
    INDEX
    Explanations

    relatives describing past events

    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
     αξιο
    -0.08
    å¦ĤæŀľéģĩåĪ°
    -0.07
    èĭ¥åľ¨
    -0.07
    æ¯ĶæĻ®éĢļ
    -0.07
    å¦Ĥæŀľä¸Ģ个
    -0.07
    æĪijä¹Łä¼ļ
    -0.06
    ä»Ĭå¹´çļĦ
    -0.06
    å¦Ĥæŀľä½łåľ¨
    -0.06
    å¦Ĥéģĩ
    -0.06
    ivil
    -0.06
    POSITIVE LOGITS
     previously
    0.12
     previamente
    0.11
     already
    0.11
     Previously
    0.11
    already
    0.10
     altrimenti
    0.10
     originally
    0.10
     originalmente
    0.09
     zuvor
    0.09
     préal
    0.09
    Activations Density 0.304%

    No Known Activations