© 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. 3104
    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
     èĭ¥è¦ģ
    -0.23
    åĵģçīĮ形象
    -0.23
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.23
    è°¡
    -0.22
    åµĽ
    -0.21
     çünkü
    -0.21
    /Dk
    -0.21
     roma
    -0.21
    æŁ¥çľĭ详æĥħ
    -0.20
    aeda
    -0.20
    POSITIVE LOGITS
    icester
    0.25
    oref
    0.24
    alon
    0.22
    ÈĽ
    0.21
    ographics
    0.21
    ueue
    0.21
    erno
    0.21
    iguiente
    0.21
    é»ijæģ¶
    0.20
    reglo
    0.20
    Activations Density 0.000%

    No Known Activations