© 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. 15451
    Prev
    Next
    INDEX
    Explanations

    subtle difference or small change

    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
    illis
    -0.09
    æĸŃäºĨ
    -0.08
    RIES
    -0.08
    人æĿ¥
    -0.08
    åѤåĦ¿
    -0.08
     fria
    -0.08
    æĸŃ
    -0.08
    ymes
    -0.07
     plena
    -0.07
    gars
    -0.07
    POSITIVE LOGITS
     subtle
    0.09
    å·®åĪ«
    0.09
     difference
    0.09
    ç»Ĩå¾®
    0.09
    å¾®è°ĥ
    0.09
     incremental
    0.08
    å·®å¼Ĥ
    0.08
     barely
    0.07
    Increment
    0.07
    .bb
    0.07
    Activations Density 0.072%

    No Known Activations