© 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. 1281
    Prev
    Next
    INDEX
    Explanations

    US states and cities

    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
    byss
    -0.25
    åĻĻ
    -0.23
     ×Ķ×ķ×ĵ
    -0.22
    ASHINGTON
    -0.22
    .fromRGBO
    -0.21
    observeOn
    -0.21
     appréci
    -0.21
    readcr
    -0.21
    å¦Ĥæŀľçݩ家
    -0.20
    âĺ°
    -0.20
    POSITIVE LOGITS
    å·ŀ
    0.24
    ian
    0.23
    ensis
    0.22
    åľ°åĮºçļĦ
    0.22
    -region
    0.22
    irut
    0.21
    å·ŀå¸Ĥ
    0.21
    -Israel
    0.21
    åľ°åĮº
    0.20
    laces
    0.20
    Activations Density 3.876%

    No Known Activations