© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    headers or beginnings

    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
    )↵↵↵↵↵↵↵↵
    -0.23
     nigeria
    -0.22
    usercontent
    -0.21
    PCS
    -0.21
    âĸ¿
    -0.20
    edly
    -0.20
    .setPrototypeOf
    -0.20
    :<?
    -0.20
    zyst
    -0.20
    åĹ¾
    -0.19
    POSITIVE LOGITS
     occupants
    0.20
     helt
    0.19
     negó
    0.18
     fortn
    0.18
    ulent
    0.18
    Coll
    0.17
    æľŁæĿĥ
    0.17
    è¶ĬãģĹ
    0.17
     occup
    0.17
     sentences
    0.17
    Activations Density 0.005%

    No Known Activations