© 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. 22984
    Prev
    Next
    INDEX
    Explanations

    parts of proper 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
    -suite
    -0.06
    ANEL
    -0.06
    æºĸ
    -0.06
    罩
    -0.06
    ä¹İ
    -0.06
    éĽ¨éľ²
    -0.06
     untreated
    -0.06
    æĿĪ
    -0.06
    壳
    -0.06
    زÙĬÙĨ
    -0.05
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.09
     appunto
    0.09
    GuidId
    0.09
    GenerationStrategy
    0.08
    è¿Ļ个åIJįåŃĹ
    0.08
    EmptyEntries
    0.08
    æĹ¥æ¸¸
    0.08
    omething
    0.08
    URLException
    0.08
    byname
    0.08
    Activations Density 0.035%

    No Known Activations