© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    technical or specific

    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
     milano
    -0.23
    ±ħ
    -0.22
    âŀ¤
    -0.22
     démarch
    -0.21
    被èªī
    -0.20
    èµħ
    -0.20
     przecież
    -0.20
    å¨ģåIJį
    -0.19
    è¿Ļä¸ªåľ°åĽ¾
    -0.19
    .vo
    -0.19
    POSITIVE LOGITS
    stdarg
    0.23
     FetchType
    0.23
     ($('#
    0.19
     METH
    0.19
    -Mail
    0.19
    ÑĨиалÑĮно
    0.18
     {?>↵
    0.18
     SqlDataAdapter
    0.18
    IGHL
    0.18
    epam
    0.18
    Activations Density 0.001%

    No Known Activations