© 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. 38481
    Prev
    Next
    INDEX
    Explanations

    express or representation

    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
    yeong
    -0.08
    yka
    -0.08
    æľīçĶŁ
    -0.07
    tep
    -0.07
    åĪ©
    -0.07
    qc
    -0.07
    egger
    -0.07
    åĪ©çī©
    -0.07
    idth
    -0.07
    iego
    -0.06
    POSITIVE LOGITS
     express
    0.08
     Express
    0.08
     expressing
    0.08
    表达
    0.08
     rempla
    0.07
     expresses
    0.07
    Express
    0.07
    convert
    0.07
     ausdr
    0.07
    åª
    0.07
    Activations Density 0.003%

    No Known Activations