© 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. 38084
    Prev
    Next
    INDEX
    Explanations

    positive evaluations including 'good' or 'great'

    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
    bung
    -0.06
    SUPER
    -0.06
     poorest
    -0.06
    æĪĸåħ¶å®ĥ
    -0.06
    æĥĬ
    -0.06
    mio
    -0.06
     Harr
    -0.06
     poor
    -0.06
    ying
    -0.06
    æ¸ħæ¥ļ
    -0.06
    POSITIVE LOGITS
    ä¹Łå¾Ī大
    0.11
    ä¹ŁéĿŀ常
    0.10
    ä¹Łä¸įéĶĻ
    0.10
    ä¹Łå¾Ī好
    0.10
    ä¹Łå¾Īå¤ļ
    0.10
    ä¹ŁæĮº
    0.09
    ä¹Łå¾Ī
    0.09
    ibling
    0.09
    ä»ħ次äºİ
    0.09
    ä¹Łæĺ¯éĿŀ常
    0.09
    Activations Density 0.096%

    No Known Activations