© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2619
    Prev
    Next
    INDEX
    Explanations

    company merger

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĴ«
    -0.23
     //[
    -0.23
    -scrollbar
    -0.21
     whiteColor
    -0.20
    èIJ½åľ°
    -0.19
    istema
    -0.19
     BoxDecoration
    -0.19
     StringComparison
    -0.19
    ä¸ªèµĽåŃ£
    -0.19
     '../../../../../
    -0.18
    POSITIVE LOGITS
    :".$
    0.26
    èĤ¡ä¸ľå¤§ä¼ļ
    0.25
    åħ¬åı¸çļĦ
    0.25
    âĦī
    0.24
    å·¨
    0.24
    æīŃ
    0.23
    äºĨ好å¤ļ
    0.23
    :'.$
    0.23
     company
    0.23
     merg
    0.23
    Activations Density 0.654%

    No Known Activations