© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 759
    Prev
    Next
    INDEX
    Explanations

    specific terms

    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
     démarch
    -0.46
    åĭł
    -0.46
     nouve
    -0.38
    å°±å¤Ł
    -0.36
    ä¿Ŀ驾
    -0.36
    /Runtime
    -0.35
    /Dk
    -0.35
    å¬Ĺ
    -0.35
    è¸Ķ
    -0.34
     informatie
    -0.33
    POSITIVE LOGITS
     burge
    0.37
     misunder
    0.35
     unfavor
    0.31
    serir
    0.30
    arrings
    0.30
     gunmen
    0.29
    bserv
    0.28
    jong
    0.28
     пÑĢедÑĥÑģмоÑĤÑĢен
    0.27
    bsite
    0.27
    Activations Density 1.165%

    No Known Activations