© 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. 30835
    Prev
    Next
    INDEX
    Explanations

    whole, overall, summary, collection, totals

    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
    çĤĻ
    -0.08
    ambe
    -0.08
    iological
    -0.08
    æ¥
    -0.07
    protocol
    -0.07
    nodoc
    -0.07
    insen
    -0.07
    нов
    -0.07
    ergency
    -0.07
    pmat
    -0.07
    POSITIVE LOGITS
    æķ´ä½ĵçļĦ
    0.22
    æķ´ä½ĵ
    0.20
    çļĦæķ´ä½ĵ
    0.19
     overall
    0.18
    æķ´é«Ķ
    0.16
    overall
    0.16
    æķ´ä½ĵä¸Ĭ
    0.15
     whole
    0.15
    Overall
    0.15
     Overall
    0.15
    Activations Density 0.192%

    No Known Activations