© 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. 40409
    Prev
    Next
    INDEX
    Explanations

    report findings

    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
     practise
    -0.08
    ยิà¸Ļ
    -0.08
    ç»ıæµİæĸ°éĹ»
    -0.07
    ãĤ»ãĥ³ãĥĪ
    -0.07
    èŀº
    -0.07
    è¨Ģä¼ł
    -0.07
    remen
    -0.07
    æĹłå¤Ħ
    -0.07
    ä¼ģä¸ļæĸ°éĹ»
    -0.07
    æĶ¯éħį
    -0.07
    POSITIVE LOGITS
     report
    0.14
    æĬ¥åijĬä¸Ń
    0.13
    æĬ¥åijĬ
    0.12
    åĪĨæŀIJæĬ¥åijĬ
    0.12
    æĬ¥åijĬçļĦ
    0.12
     Report
    0.12
     reports
    0.11
    çļĦæĬ¥åijĬ
    0.11
    åł±åijĬ
    0.11
     findings
    0.10
    Activations Density 0.411%

    No Known Activations