© 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. 63410
    Prev
    Next
    INDEX
    Explanations

    transferring or switching possession

    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
    .dep
    -0.09
    æĬĺèħ¾
    -0.07
    anska
    -0.07
    nip
    -0.07
    éĹ®ä¸ĸ
    -0.07
    saan
    -0.07
    åıĤèµĽä½ľåĵģ
    -0.07
    QueryBuilder
    -0.07
    .sep
    -0.07
    åij¤
    -0.07
    POSITIVE LOGITS
    转移
    0.13
     transferred
    0.11
     transfer
    0.11
    transfer
    0.11
     Transfer
    0.11
    æݥ管
    0.10
     transferring
    0.09
     inherit
    0.09
    Transfer
    0.09
    è½ī移
    0.09
    Activations Density 0.300%

    No Known Activations