© 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. 896
    Prev
    Next
    INDEX
    Explanations

    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
     “
    -0.25
    ------+------+
    -0.23
     (
    -0.23
     (“
    -0.23
     simply
    -0.22
    (
    -0.22
     too
    -0.22
     ‘
    -0.21
    çĶļèĩ³
    -0.21
     merely
    -0.21
    POSITIVE LOGITS
    -Headers
    0.34
    èĩ³å°ij
    0.32
    :".$
    0.28
    }_${
    0.27
    å°ijãģªãģı
    0.27
    ]int
    0.26
    aniu
    0.24
    herits
    0.24
    .debian
    0.24
    ç½ijé¦ĸ页
    0.24
    Activations Density 1.553%

    No Known Activations