© 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. 866
    Prev
    Next
    INDEX
    Explanations

    code and 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
    ábado
    -0.28
     Unsure
    -0.27
    -threat
    -0.26
     Stamina
    -0.26
    ÅĤuż
    -0.25
    âĹĤ
    -0.25
     Insets
    -0.24
    âĨ¤
    -0.23
     semiclass
    -0.23
    stringLiteral
    -0.23
    POSITIVE LOGITS
    :"#
    0.25
    çIJļ
    0.22
    lucent
    0.22
    :'#
    0.22
    App
    0.22
     winger
    0.21
    á¼Ķ
    0.21
    å¹´ä¹ĭ
    0.21
    	Copyright
    0.21
     The
    0.20
    Activations Density 2.071%

    No Known Activations