© 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. 9047
    Prev
    Next
    INDEX
    Explanations

    quotation ending punctuation

    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
    eister
    -0.09
    åd
    -0.09
    éķ¿æĮīäºĮç»´çłģ
    -0.08
    ä½Ĩæĺ¯åĽłä¸º
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    áĥĶáĥĵ
    -0.08
    ä»ĸè·Ł
    -0.08
    åı«åģļ
    -0.08
    è¿Ļ个æĺ¯
    -0.08
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.07
    POSITIVE LOGITS
    enf
    0.07
    ëł
    0.07
    究竣æĺ¯ä»Ģä¹Ī
    0.06
    vient
    0.06
    æ¤
    0.06
    溯
    0.06
    Drawing
    0.06
    ách
    0.06
    Assertions
    0.06
    ä¸į容忽è§Ĩ
    0.06
    Activations Density 0.003%

    No Known Activations