© 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. 3726
    Prev
    Next
    INDEX
    Explanations

    identifiers and specific names

    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
    opportunitÃł
    -0.23
    poons
    -0.22
    åģ¶
    -0.22
    ickname
    -0.21
    /*↵
    -0.19
    ıy
    -0.19
    æ·ĺ
    -0.19
    SPATH
    -0.19
    ä¸ī大éĺ¶æ®µ
    -0.19
     natural
    -0.18
    POSITIVE LOGITS
    ï¼ģ');↵
    0.24
    ä¸Ģèĩ´å¥½è¯Ħ
    0.23
     -->↵↵↵
    0.22
    xia
    0.22
    åħ¨åĬĽä»¥
    0.22
     "(\<
    0.21
    -END
    0.21
     âĨĴ↵↵
    0.21
     Merrill
    0.20
    endencies
    0.20
    Activations Density 0.001%

    No Known Activations