© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3136
    Prev
    Next
    INDEX
    Explanations

    numbers and technical 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
    %!
    -0.28
    anter
    -0.27
    å¹´ä¹ĭä¹ħ
    -0.24
    :'.$
    -0.23
    .assertj
    -0.21
    :';↵
    -0.21
    dden
    -0.21
     Tantra
    -0.21
    -BEGIN
    -0.21
    âĺħâĺħ
    -0.21
    POSITIVE LOGITS
    paralleled
    0.20
    å§Ķç»Ħç»ĩ
    0.20
     Graz
    0.20
    _paid
    0.19
    iston
    0.19
     oui
    0.19
     removeObject
    0.19
    put
    0.19
    InMillis
    0.18
     consolation
    0.18
    Activations Density 0.004%

    No Known Activations