© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4009
    Prev
    Next
    INDEX
    Explanations

    people and roles

    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
     Decompiled
    -0.27
    å¿ŀ
    -0.24
    adiens
    -0.23
    bak
    -0.22
    zcze
    -0.22
    ','');↵
    -0.22
    ickerView
    -0.22
    .labelX
    -0.21
    /Internal
    -0.21
    elves
    -0.21
    POSITIVE LOGITS
    çĶ³è¯·äºº
    0.32
    æĤ£èĢħçļĦ
    0.30
    æľ¬äºº
    0.28
    åѦçĶŁçļĦ
    0.27
    å½ĵäºĭ
    0.27
    èĢĥçĶŁ
    0.27
    主人åħ¬
    0.27
    éĢīæīĭ
    0.26
    è¿ĻåIJį
    0.26
    æĤ£èĢħ
    0.26
    Activations Density 0.639%

    No Known Activations