© 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. 26593
    Prev
    Next
    INDEX
    Explanations

    difference and differential

    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
    è¿ŀè¿ŀ
    -0.07
    æī¼
    -0.06
    ÅĤuż
    -0.06
    .Embed
    -0.06
    ROOT
    -0.06
    åıĤæĶ¿
    -0.06
     Ball
    -0.06
    ICE
    -0.06
    ÙĦاÙħ
    -0.06
    临
    -0.06
    POSITIVE LOGITS
     difference
    0.22
    difference
    0.21
    ä¹ĭå·®
    0.20
     Difference
    0.20
    Difference
    0.20
    å·®å¼Ĥ
    0.20
     differences
    0.19
    å·®
    0.19
     ÑĢазниÑĨа
    0.17
     Differences
    0.17
    Activations Density 0.037%

    No Known Activations