© 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. 21626
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by question words

    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
    å¨Ĩ
    -0.08
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.08
    以ä¸ĭ为
    -0.07
    éĶIJæĦı
    -0.07
    交éģĵ
    -0.07
    ãģ¨è¨Ģãģ£ãģ¦ãĤĤ
    -0.07
    iquer
    -0.06
    çł¥çłºåīįè¡Į
    -0.06
    è¦ģä¸¥æł¼
    -0.06
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.06
    POSITIVE LOGITS
    èĢĮè¿ĻäºĽ
    0.09
     surely
    0.08
    éļ¾éģĵ
    0.08
    çĶ±æѤåı¯è§ģ
    0.08
     rethink
    0.08
    æį¢æĪIJ
    0.08
    è¿Ļå°±æĺ¯
    0.08
    åı¯è§ģ
    0.07
    èĢĮéĤ£äºĽ
    0.07
    æĥ³åĪ°è¿ĻéĩĮ
    0.07
    Activations Density 0.474%

    No Known Activations