© 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. 30573
    Prev
    Next
    INDEX
    Explanations

    organizations, groups, associations, clubs, branches

    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
    paired
    -0.08
    éķĩéĿĻ
    -0.06
     paired
    -0.06
    /error
    -0.06
    æĭīå¼ĢäºĨ
    -0.06
    ä¸ĩè¾¾å¹¿åľº
    -0.06
    åĢ¼çıŃ
    -0.06
     substituted
    -0.06
     isot
    -0.06
     زÛĮب
    -0.06
    POSITIVE LOGITS
     membership
    0.14
    Membership
    0.13
    ç»Ħç»ĩ
    0.12
     Membership
    0.12
     memberships
    0.12
    æĪIJç«ĭäºİ
    0.12
    _membership
    0.12
    çļĦæĪIJåijĺ
    0.12
     organization
    0.12
    ç»Ħç»ĩçļĦ
    0.12
    Activations Density 0.630%

    No Known Activations