© 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. 3248
    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
    ($('<
    -0.24
    éĻIJæŶ
    -0.22
     acompaña
    -0.21
    iffany
    -0.20
    ants
    -0.20
    ðŁĵIJ
    -0.20
    POSIT
    -0.20
    âĦľ
    -0.20
    isclosed
    -0.20
    个åĪ«
    -0.20
    POSITIVE LOGITS
    -UA
    0.22
    Tot
    0.21
    peare
    0.20
    itez
    0.20
    pecially
    0.20
    atile
    0.20
     compared
    0.19
    骶
    0.19
    æģ«
    0.19
    keypress
    0.19
    Activations Density 0.430%

    No Known Activations