© 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. 2226
    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
    æĹłè®ºæĺ¯åħ¶
    -0.21
    ingleton
    -0.20
     enthus
    -0.20
     OnTrigger
    -0.20
    esModule
    -0.20
    elerik
    -0.19
    /AFP
    -0.19
    uetype
    -0.19
    InputModule
    -0.19
    loquent
    -0.19
    POSITIVE LOGITS
    /moment
    0.22
    裸
    0.21
    atsby
    0.21
    kiem
    0.19
    izza
    0.19
    è·
    0.19
    CLUDED
    0.19
    åħ¬æĸ¤
    0.18
    ati
    0.18
    ufacturer
    0.18
    Activations Density 0.000%

    No Known Activations