© 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. 29770
    Prev
    Next
    INDEX
    Explanations

    predicting outcomes and rules

    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
    תר
    -0.09
    zehn
    -0.08
    antaran
    -0.08
    ÑĩеÑĢед
    -0.08
    atics
    -0.08
    ilton
    -0.08
    ÑĤаки
    -0.07
    -bodied
    -0.07
    antry
    -0.07
    à¸Ĥว
    -0.07
    POSITIVE LOGITS
    à¸ģารà¸ĵà¹Į
    0.09
    éĢļãĤĬãģ®
    0.08
    /pre
    0.08
    é¢ĦæĬ¥
    0.08
    enho
    0.08
    ably
    0.08
    éĢļãĤĬãģ«
    0.08
    ÙĬØ©
    0.08
    åĴĮ建议
    0.08
    æĪIJ羣
    0.08
    Activations Density 0.034%

    No Known Activations