© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 848
    Prev
    Next
    INDEX
    Explanations

    citations or references

    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
     Promo
    -0.23
     promo
    -0.20
     reelection
    -0.20
     cig
    -0.19
    //**↵
    -0.18
    agi
    -0.18
    ;};↵
    -0.18
    èĪ¬
    -0.18
    bsites
    -0.18
     bör
    -0.18
    POSITIVE LOGITS
    áħŁ
    0.27
    }elseif
    0.22
    gements
    0.21
    ABSPATH
    0.20
     Springer
    0.20
    presso
    0.20
    إبر
    0.20
    airo
    0.20
    sap
    0.20
    èĦ±ç¦»
    0.20
    Activations Density 0.399%

    No Known Activations