© 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. 2948
    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
    -0.23
    伦
    -0.22
     modal
    -0.20
    lucent
    -0.20
     Tec
    -0.20
    alta
    -0.20
     contr
    -0.19
    ollipop
    -0.19
     Decompiled
    -0.19
    'Connor
    -0.19
    POSITIVE LOGITS
    iad
    0.23
     Ãĸzellikle
    0.21
    ãĥ¬ãĥĵ
    0.21
    ;break
    0.21
     AppleWebKit
    0.20
     Ãĸnceki
    0.20
    %@",
    0.20
    éĻ¢éĻ¢éķ¿
    0.20
     Bugün
    0.20
    veau
    0.19
    Activations Density 0.023%

    No Known Activations