© 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. 30146
    Prev
    Next
    INDEX
    Explanations

    pot and facet openers

    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
    ault
    -0.08
    åµĺ
    -0.08
    otch
    -0.08
    olley
    -0.08
    avas
    -0.08
    koch
    -0.08
    rakt
    -0.07
    ↵            ↵
    -0.07
    erton
    -0.07
     ↵            ↵
    -0.07
    POSITIVE LOGITS
     Pot
    0.07
     pot
    0.07
    Pot
    0.07
    并使çĶ¨
    0.06
    e
    0.06
    并æıIJ交
    0.06
    ç½ļ
    0.06
    ï½Ĺï½Ĺ
    0.06
    мо
    0.06
     facet
    0.06
    Activations Density 0.001%

    No Known Activations