© 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. 3200
    Prev
    Next
    INDEX
    Explanations

    like

    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
     Kardash
    -0.22
    å°ıæŶåīį
    -0.22
    buah
    -0.21
    éŃĩ
    -0.20
     flatten
    -0.20
     babe
    -0.20
    æ¹¾
    -0.19
     proximité
    -0.19
     ones
    -0.19
     incompet
    -0.19
    POSITIVE LOGITS
    ornings
    0.27
    NOWLED
    0.25
    ////////////////////////////////////////////////////////
    0.24
    uxtap
    0.23
    SURE
    0.23
    serter
    0.23
     najbli
    0.23
    Investigators
    0.23
    orgeous
    0.23
    ?('
    0.23
    Activations Density 0.135%

    No Known Activations