© 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. 16098
    Prev
    Next
    INDEX
    Explanations

    studies

    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
    argins
    -0.07
    æ»ļå±ı
    -0.07
    aat
    -0.07
    ä¸įæĹ©
    -0.06
    icks
    -0.06
    .LOC
    -0.06
    akter
    -0.06
    ides
    -0.06
    é¬
    -0.06
    ede
    -0.06
    POSITIVE LOGITS
    äch
    0.07
    ANDLE
    0.07
    å¤ĸåIJij
    0.07
     GuÃŃa
    0.07
    好çļĦ
    0.07
    ertest
    0.07
    å¤ĩ
    0.07
    ä¸ĬæľĪ
    0.06
    erala
    0.06
    å¦ĸéŃĶ
    0.06
    Activations Density 0.005%

    No Known Activations