© 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. 1845
    Prev
    Next
    INDEX
    Explanations

    identifying specific entities

    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
     necessitÃł
    -0.20
    stands
    -0.19
     fieldName
    -0.19
    ç«ĭ
    -0.19
     ?>"/>↵
    -0.19
    æįĭ
    -0.19
    ery
    -0.19
    HomeAsUpEnabled
    -0.18
    .nickname
    -0.18
    egen
    -0.18
    POSITIVE LOGITS
    /Dk
    0.32
    ién
    0.24
    AtA
    0.24
    благо
    0.24
    ::.
    0.23
     èĭ¥è¦ģ
    0.23
    SBATCH
    0.23
    วล
    0.22
    äºĨ好å¤ļ
    0.22
    /Internal
    0.22
    Activations Density 0.091%

    No Known Activations