© 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. 61695
    Prev
    Next
    INDEX
    Explanations

    latter, type, such

    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
    åħ¨å¥Ĺ
    -0.09
    åħ¨ä½ĵ人åijĺ
    -0.08
    anj
    -0.07
    对äºİè¿Ļ个
    -0.07
    ×Ļ×ķת
    -0.07
    æīĢæľī
    -0.07
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
     ofici
    -0.07
    åħ¨éĿ¢å»ºæĪIJ
    -0.07
    ëĮĢë¡ľ
    -0.07
    POSITIVE LOGITS
    å¾Ģå¾Ģæĺ¯
    0.15
    å¾Ģå¾Ģ
    0.15
     often
    0.14
    æľīæŶ
    0.14
     sometimes
    0.14
     Sometimes
    0.13
    æľīæŶåĢĻ
    0.13
     Often
    0.12
    Sometimes
    0.12
    å¤ļè§ģäºİ
    0.12
    Activations Density 0.150%

    No Known Activations