© 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. 28639
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by 'which'

    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
    æĵħ
    -0.06
    imismo
    -0.06
    çľ¼çľĭ
    -0.06
    ä»İä»ĸ
    -0.06
    ä½łåij¢
    -0.06
     a
    -0.06
    为ä¸Ģ
    -0.06
    å¾Ģ
    -0.05
    UEL
    -0.05
    ам
    -0.05
    POSITIVE LOGITS
     which
    0.14
     коÑĤоÑĢом
    0.12
     коÑĤоÑĢой
    0.12
     οÏĢοία
    0.12
     οÏĢοίο
    0.12
    which
    0.12
     οÏĢοί
    0.11
     коÑĤоÑĢÑĭÑħ
    0.11
     whereby
    0.11
    .which
    0.11
    Activations Density 0.140%

    No Known Activations