© 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. 43677
    Prev
    Next
    INDEX
    Explanations

    written instructions or forms

    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
     itself
    -0.16
     którego
    -0.12
    коÑĤоÑĢ
    -0.12
     коÑĤоÑĢомÑĥ
    -0.11
    诸
    -0.10
     koju
    -0.10
    ளà¯įளதà¯ģ
    -0.10
    ிறதà¯ģ
    -0.10
    ä¹Łæĺ¯ä¸Ģ个
    -0.10
     magát
    -0.10
    POSITIVE LOGITS
     themselves
    0.31
     kojima
    0.21
     коÑĤоÑĢÑĭе
    0.19
     denen
    0.18
     ones
    0.18
     amelyek
    0.18
     thems
    0.18
     Ø£ÙĨÙģسÙĩÙħ
    0.17
    ä¸Ģ个个
    0.17
     jotka
    0.17
    Activations Density 3.986%

    No Known Activations