© 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. 1469
    Prev
    Next
    INDEX
    Explanations

    software features

    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
     boobs
    -0.32
    Ø¥ÙħÙĥاÙĨ
    -0.30
     perpetr
    -0.29
     snapchat
    -0.28
     hoodie
    -0.28
     diner
    -0.25
    عطÙĬ
    -0.24
     panties
    -0.23
     hentai
    -0.23
     motel
    -0.23
    POSITIVE LOGITS
    Ũ
    0.35
    ipop
    0.33
    esub
    0.33
    ynos
    0.33
    ngth
    0.32
    ancements
    0.31
    rlen
    0.31
    outil
    0.31
    méd
    0.31
    asurer
    0.30
    Activations Density 12.713%

    No Known Activations