© 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. 1497
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     (*((
    -0.26
     çĶŁåij½åij¨æľŁ
    -0.26
     }}>{
    -0.23
     (~(
    -0.21
     licensors
    -0.20
     "");↵↵
    -0.20
     '');↵↵
    -0.20
     '{$
    -0.20
     panties
    -0.20
     ((_
    -0.20
    POSITIVE LOGITS
    -Semit
    0.27
    slaught
    0.27
    ubbo
    0.26
     if
    0.25
    :animated
    0.24
    æľīçĶ¨çļĦ
    0.23
     //
    0.23
    ìm
    0.23
    bsolute
    0.23
    å§ĭ建
    0.23
    Activations Density 0.609%

    No Known Activations