© 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. 2738
    Prev
    Next
    INDEX
    Explanations

    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
    ('<?
    -0.22
     esac
    -0.20
     if
    -0.20
    azı
    -0.19
     If
    -0.19
    çĽ¥
    -0.19
    .OnClickListener
    -0.19
     try
    -0.19
    ĺìĿ´
    -0.19
    .addData
    -0.18
    POSITIVE LOGITS
    ",-
    0.24
     ún
    0.24
    zych
    0.22
    blick
    0.22
    UDGE
    0.21
     libertin
    0.21
     roma
    0.21
    ".↵↵↵↵
    0.21
     pestic
    0.21
     bergen
    0.21
    Activations Density 0.069%

    No Known Activations