© 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. 23269
    Prev
    Next
    INDEX
    Explanations

    engine parts and accessories

    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
    è¶
    -0.08
    ç³Ļ
    -0.07
    åħ´
    -0.07
    èµ·ä¼ı
    -0.06
     Portable
    -0.06
     Gutenberg
    -0.06
    交éĢļå·¥åħ·
    -0.06
     Julia
    -0.06
    Chunk
    -0.06
     Jain
    -0.06
    POSITIVE LOGITS
    æĢ»æĪIJ
    0.10
     aftermarket
    0.09
     replacement
    0.08
    ãĤ¢ãĤ¤ãĥīãĥ«
    0.08
    tridge
    0.08
    older
    0.08
     accessory
    0.08
    ernal
    0.07
     rear
    0.07
     Replacement
    0.07
    Activations Density 0.272%

    No Known Activations