© 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. 62187
    Prev
    Next
    INDEX
    Explanations

    after prepositions

    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
    icola
    -0.08
    aed
    -0.08
    +xml
    -0.07
    ÙĤÙĦÙĬ
    -0.07
    اÛĮد
    -0.07
    ä¹ĭ为
    -0.07
    èĢĮè¨Ģä¹ĭ
    -0.07
    ä¹ĭæīį
    -0.07
    дÑĢе
    -0.07
    urf
    -0.07
    POSITIVE LOGITS
    ä»ĭçŁ³
    0.10
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    tings
    0.07
    ãĥ¡ãĥ³ãĥĪ
    0.07
    ẵ
    0.06
    ×Ļ×Ļ×Ŀ
    0.06
    britannien
    0.06
    -fashioned
    0.06
    /down
    0.06
    ê³±
    0.06
    Activations Density 1.998%

    No Known Activations