© 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. 2997
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ipherals
    -0.26
    <fieldset
    -0.23
    alborg
    -0.23
    uxtap
    -0.22
    ERNEL
    -0.21
    Spacer
    -0.21
    //}↵↵
    -0.21
    ãĥĨãĤ£ãĥ¼
    -0.21
    ehicle
    -0.21
    ãĥµ
    -0.20
    POSITIVE LOGITS
     xOffset
    0.21
    ancock
    0.20
    amp
    0.20
     (;;
    0.20
    ç®ĹäºĨ
    0.19
    èµĢ
    0.19
    æĺ¯ä¸Ģéĥ¨
    0.19
     ragazzi
    0.19
    è¿ŀèĥľ
    0.19
    inston
    0.19
    Activations Density 0.308%

    No Known Activations