© 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. 1758
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    icester
    -0.27
    åħ¨èµĦåŃIJ
    -0.25
    roof
    -0.21
    ItemSelectedListener
    -0.20
    mite
    -0.20
     Playoff
    -0.20
     ActiveForm
    -0.20
    lobe
    -0.20
    Tanggal
    -0.19
    >--
    -0.19
    POSITIVE LOGITS
     cass
    0.21
    ellen
    0.20
    æĿ¡è¯Ħ论
    0.20
    .ibatis
    0.20
    ergus
    0.19
     Cass
    0.18
    éļĨéĩį举è¡Į
    0.18
    @endforeach
    0.18
    aries
    0.18
    ⣶
    0.18
    Activations Density 0.490%

    No Known Activations