© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 23501
    Prev
    Next
    INDEX
    Explanations

    that it

    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
    æį®
    -0.09
     reportedly
    -0.09
    æį®æĬ¥éģĵ
    -0.08
    æį®äºĨè§£
    -0.08
    æį®è¯´
    -0.08
    æĪijè®°å¾Ĺ
    -0.08
    åĪ«å¿ĺäºĨ
    -0.07
    å½ĵçĦ¶è¦ģ
    -0.07
    æį®æĤī
    -0.07
    æį®ç»Łè®¡
    -0.07
    POSITIVE LOGITS
    ä¸Ģæĸij
    0.13
    端åĢª
    0.12
    ä¸į对åĬ²
    0.08
    大éĥ¨åĪĨéĥ½æĺ¯
    0.08
    以ä¸ĭåĨħ容
    0.08
    èĩ³å°ijæľī
    0.08
     neither
    0.08
    ä¸įå¦Ļ
    0.08
    è¿Ļæĺ¯ä¸Ģ个
    0.08
    以ä¸ĭåĩłçĤ¹
    0.08
    Activations Density 0.185%

    No Known Activations