© 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. 33
    Prev
    Next
    INDEX
    Explanations

    noun suffixes

    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
    åij²
    -0.28
    âĨ©
    -0.23
    游æĪıè§Ĵèī²
    -0.23
    â¬ĩ
    -0.22
    æīĭæľºçīĪ
    -0.21
    ÙĥÙĪرÙĪÙĨا
    -0.21
    vanished
    -0.21
    çĸ¥
    -0.20
    à¸ģรม
    -0.20
    ä»İæł¹æľ¬
    -0.19
    POSITIVE LOGITS
    ilty
    0.36
    ity
    0.32
    ITY
    0.30
    mente
    0.28
    ypse
    0.27
    idad
    0.27
     prostitu
    0.26
    ities
    0.26
    ness
    0.26
    ität
    0.25
    Activations Density 6.249%

    No Known Activations