© 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. 51843
    Prev
    Next
    INDEX
    Explanations

    red shift and big bang theory

    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
    æĬĺ
    -0.08
    ä¸įå¤ĸ
    -0.07
    为æ¶Īè´¹èĢħ
    -0.07
    éļ¾ä»¥å¿ĺæĢĢ
    -0.07
     "<?
    -0.07
    uard
    -0.06
    æĸ¹åľĨ
    -0.06
    羽翼
    -0.06
    åħĭåħ°
    -0.06
     cam
    -0.06
    POSITIVE LOGITS
    velocity
    0.09
    Velocity
    0.09
    天涯
    0.09
    离æĪij们
    0.09
     velocity
    0.08
     galaxies
    0.08
    -distance
    0.08
    _velocity
    0.08
     accelerating
    0.08
    istant
    0.08
    Activations Density 0.004%

    No Known Activations