© 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. 3009
    Prev
    Next
    INDEX
    Explanations

    programming functions

    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
    çĤĿ
    -0.22
    /MPL
    -0.22
    //=
    -0.20
    ÐŁÐ¾Ð´ÑĢоб
    -0.19
    onen
    -0.19
    @protocol
    -0.18
    .ToShort
    -0.18
    EIF
    -0.18
    ertos
    -0.18
    éĹ®æĪij
    -0.18
    POSITIVE LOGITS
    çĤİ
    0.21
     ++)↵
    0.21
    .’”↵↵
    0.21
     inse
    0.20
    imo
    0.19
    irie
    0.19
    íijľ
    0.18
     '..',
    0.18
    .openConnection
    0.18
     proclaim
    0.18
    Activations Density 0.082%

    No Known Activations