© 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. 3417
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ç§ijçłĶéĻ¢
    -0.26
    ç½ijé¦ĸ页
    -0.25
    ç¾İåªĴ
    -0.23
    女æĢ§æľĭåıĭ
    -0.21
    åĮ»ç§ij
    -0.21
    欸
    -0.21
    é£Łãģ¹ãģ¦
    -0.20
    ä¸ĵçĶ¨
    -0.20
    ï¼±
    -0.20
    éĹªè¿ĩ
    -0.20
    POSITIVE LOGITS
    plemented
    0.21
    endencies
    0.21
    reo
    0.20
    aniu
    0.19
    evin
    0.19
     removeFrom
    0.19
    odom
    0.19
    .checkSelfPermission
    0.19
    emma
    0.19
    esub
    0.18
    Activations Density 0.001%

    No Known Activations