© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1813
    Prev
    Next
    INDEX
    Explanations

    say pronouns

    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
    ///č↵
    -0.24
    .numberOfLines
    -0.21
    nÄħ
    -0.21
    ().'/
    -0.21
    "value
    -0.21
    "label
    -0.20
    ABCDEFGHIJKLMNOP
    -0.20
    á»ĩc
    -0.20
    -Bold
    -0.20
    yrı
    -0.20
    POSITIVE LOGITS
    å®ĥ
    0.99
    å®ĥ们
    0.85
    å®ĥæĺ¯
    0.82
    å®ĥçļĦ
    0.79
     it
    0.76
    å®ĥåı¯ä»¥
    0.75
     them
    0.71
    对åħ¶è¿Ľè¡Į
    0.66
     its
    0.65
     thereof
    0.65
    Activations Density 6.649%

    No Known Activations