© 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. 10844
    Prev
    Next
    INDEX
    Explanations

    international followed by global concepts

    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
    indsight
    -0.09
    gett
    -0.08
    /response
    -0.07
    æ®ĸ
    -0.07
    atology
    -0.07
    .jquery
    -0.07
    शà¥Ģ
    -0.07
    ifero
    -0.07
    unte
    -0.07
    èIJ¦
    -0.07
    POSITIVE LOGITS
    足èģĶ
    0.10
    közi
    0.09
    angible
    0.09
    ization
    0.08
    isation
    0.08
    ität
    0.08
    /local
    0.08
    opes
    0.08
    ized
    0.07
    ities
    0.07
    Activations Density 0.036%

    No Known Activations