© 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. 2581
    Prev
    Next
    INDEX
    Explanations

    similarity expression

    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
    azu
    -0.07
    neau
    -0.07
    olet
    -0.06
     elo
    -0.06
    inet
    -0.06
    esh
    -0.06
    æĸĮ
    -0.06
    thus
    -0.06
    iene
    -0.06
    apter
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.11
     likewise
    0.10
     Likewise
    0.09
    киÑĪе
    0.09
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.09
     ÑĤоже
    0.09
    ãģĵãģ¡ãĤīãĤĤ
    0.08
     similarly
    0.08
     ìĹŃìĭľ
    0.08
    Ñģполни
    0.08
    Activations Density 0.063%

    No Known Activations