© 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. 3162
    Prev
    Next
    INDEX
    Explanations

    Scandinavia/Norway

    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
     både
    -0.32
    linky
    -0.23
     små
    -0.22
    .SetParent
    -0.20
     går
    -0.20
    å¤įå·¥å¤į
    -0.20
    GRES
    -0.20
     vår
    -0.19
    =logging
    -0.19
    æĬ½çĥŁ
    -0.19
    POSITIVE LOGITS
    åĨ°
    0.28
     ice
    0.27
     polar
    0.25
     ski
    0.24
    åĮĹæŀģ
    0.23
    irlines
    0.23
     Arctic
    0.23
     Needle
    0.23
    æĮªå¨ģ
    0.23
    âĿĦ
    0.22
    Activations Density 1.552%

    No Known Activations