© 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. 40110
    Prev
    Next
    INDEX
    Explanations

    finite difference operator

    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
    igans
    -0.08
    ONGL
    -0.08
    æĿ¥çĶµ
    -0.08
    agne
    -0.08
    ļĮ
    -0.08
    edList
    -0.08
    igas
    -0.07
     rÃłng
    -0.07
    汤åĮĻ
    -0.07
    bons
    -0.07
    POSITIVE LOGITS
     operator
    0.08
     operators
    0.08
    -operator
    0.07
    Operator
    0.07
     Delta
    0.07
    à¸ģรà¸ĵà¹Į
    0.07
    operator
    0.07
     Operator
    0.07
    æ²ĥæĸ¯
    0.07
    äºĶ天
    0.07
    Activations Density 0.001%

    No Known Activations