© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1888
    Prev
    Next
    INDEX
    Explanations

    value or effect

    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
    currentColor
    -0.26
    -Semit
    -0.25
    âļĹ
    -0.24
    'post
    -0.24
    âĦī
    -0.24
    :normal
    -0.23
    <dd
    -0.22
    举æĸ¹è´¢å¯Į
    -0.22
    <fieldset
    -0.22
    ðŁĵIJ
    -0.22
    POSITIVE LOGITS
    åľ¨äºİ
    0.26
    /import
    0.26
    ä½ĵçİ°åľ¨
    0.25
    æ·±è¿ľ
    0.23
    åįģ足
    0.21
    ful
    0.21
     coefficient
    0.21
    ç³»æķ°
    0.20
    ability
    0.20
     factor
    0.20
    Activations Density 3.536%

    No Known Activations