© 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. 46535
    Prev
    Next
    INDEX
    Explanations

    its followed by nouns

    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
    æĭ¶
    -0.08
    éļĪ
    -0.07
    ycz
    -0.07
    gant
    -0.07
     дÑı
    -0.07
    íı¬
    -0.06
    æĺµ
    -0.06
     likely
    -0.06
    ä¸įåı¯æĢĿè®®
    -0.06
    chetta
    -0.06
    POSITIVE LOGITS
    æĸ¤
    0.08
    çĦ¶åIJİåĨį
    0.07
    iore
    0.07
     à¹Ĩ
    0.07
    å°±åı¯ä»¥äºĨ
    0.07
    ä»İèĢĮ使
    0.07
    à¹Ĩ
    0.07
    iels
    0.07
     ministr
    0.07
    åħĪåĪ°
    0.07
    Activations Density 0.027%

    No Known Activations