© 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. 489
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
    REFIX
    -0.20
    icester
    -0.19
     Mediterr
    -0.19
    ledo
    -0.19
    rtle
    -0.19
     numel
    -0.18
    conexao
    -0.18
     buurt
    -0.18
     Ashe
    -0.18
    .getAmount
    -0.18
    POSITIVE LOGITS
     Decompiled
    0.22
    orget
    0.21
    isclosed
    0.21
    ÑĨиалÑĮно
    0.20
    ungeons
    0.20
     Ñģдела
    0.20
    åľ¬
    0.20
    .nodeName
    0.19
    pto
    0.19
    ecided
    0.19
    Activations Density 0.531%

    No Known Activations