© 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. 14866
    Prev
    Next
    INDEX
    Explanations

    æľī, Yahoo Holdings, google

    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
    ยà¸Ńà¸Ķ
    -0.11
    ยัà¸ĩ
    -0.10
    ยาà¸ĩ
    -0.09
    æ¯Ľæ³½ä¸ľ
    -0.09
    ãĥ£ãĥ³
    -0.09
    ä¸ĢæĮĩ
    -0.08
    ÙĨ
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    ت
    -0.08
    worthy
    -0.08
    POSITIVE LOGITS
    åĬ©äºİ
    0.15
    æĦıè¯Ĩåľ°
    0.11
    ational
    0.10
    æĶ¾çŁ¢
    0.10
    åĬŁäºİ
    0.10
    äºĨä¸Ģå®ļ
    0.09
    代表æĢ§çļĦ
    0.09
    äºĨä¸Ģå®ļçļĦ
    0.09
     lẽ
    0.09
    çĶļèĢħ
    0.08
    Activations Density 0.005%

    No Known Activations