© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21212
    Prev
    Next
    INDEX
    Explanations

    chemical composition and structure

    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
    OrCreate
    -0.08
    orsch
    -0.08
    ç±³ç²Ĵ
    -0.08
    enner
    -0.08
    igh
    -0.07
    ä¸įåīį
    -0.07
    걸
    -0.07
    æ²Ļæ²³
    -0.07
    ee
    -0.07
    ÙĤÙĬÙĩ
    -0.07
    POSITIVE LOGITS
    istry
    0.10
    ically
    0.08
    /math
    0.08
    åĵģçļĦ
    0.08
    /Math
    0.08
    alchemy
    0.08
    /material
    0.08
    飵
    0.08
    ually
    0.08
    åĴĮæĶ¿æ²»
    0.07
    Activations Density 0.046%

    No Known Activations