© 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. 938
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
    èĽ¾
    -0.20
    ¡°
    -0.20
    ЦенÑĤÑĢ
    -0.19
     numRows
    -0.19
     handleMessage
    -0.19
     HuffPost
    -0.19
    Ø«ÙĦ
    -0.18
     createSelector
    -0.18
    åŁºåĩĨ
    -0.18
    å½ĵãģ¦
    -0.18
    POSITIVE LOGITS
    ornings
    0.30
    ndern
    0.28
    /MPL
    0.28
    ãĢģãĢĮ
    0.26
    ÐŁÐµÑĤеÑĢ
    0.26
    dÃŃa
    0.25
    foundland
    0.24
    UCCESS
    0.24
     prostitu
    0.22
    ][/
    0.22
    Activations Density 0.568%

    No Known Activations