© 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. 56350
    Prev
    Next
    INDEX
    Explanations

    disparate, unrelated, diverse, varied

    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
    åŀĴ
    -0.08
    å¡
    -0.07
    าà¸Ħ
    -0.07
    appa
    -0.07
    çĴĢ
    -0.06
    à¹Īà¸Ńà¸ĩ
    -0.06
    ê¹
    -0.06
    æݨ
    -0.06
     unfortunately
    -0.06
    rawl
    -0.06
    POSITIVE LOGITS
     disparate
    0.10
    ifax
    0.08
    äºĭçī©
    0.07
     unrelated
    0.07
    iem
    0.07
    ixon
    0.07
    ubes
    0.07
    à¹Ħà¸ģล
    0.07
    omic
    0.07
    å·´åħĭ
    0.07
    Activations Density 0.002%

    No Known Activations