© 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. 2882
    Prev
    Next
    INDEX
    Explanations

    Japanese terms and concepts

    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
    欣
    -0.08
    çıĪ
    -0.08
    ún
    -0.07
    太çĽij
    -0.07
    nap
    -0.06
    漪
    -0.06
    è§ģè¯ģ
    -0.06
    éĢ
    -0.06
    iel
    -0.06
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.06
    POSITIVE LOGITS
    æ´»çĶ¨
    0.11
     Japan
    0.10
     Japanese
    0.10
    å®ŀ绩
    0.09
    ucceeded
    0.09
    éĺ²çģ¾
    0.09
    à¸įีà¹Īà¸Ľà¸¸à¹Īà¸Ļ
    0.09
    .jp
    0.09
    好ä¸į容æĺĵ
    0.09
    Japanese
    0.09
    Activations Density 3.811%

    No Known Activations