© 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. 3993
    Prev
    Next
    INDEX
    Explanations

    remainder/remaining

    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
    ernet
    -0.21
    eddar
    -0.20
    illiseconds
    -0.20
    erox
    -0.20
    usta
    -0.20
    (){}↵↵
    -0.20
    .Registry
    -0.20
    ĤŃ
    -0.20
    .MaxValue
    -0.20
    MBER
    -0.19
    POSITIVE LOGITS
    remainder
    0.29
    åī©ä¸ĭçļĦ
    0.28
    åħ¶ä½Ļ
    0.27
     remainder
    0.27
    åī©ä½Ļ
    0.25
    é¦
    0.25
    åī©ä¸ĭ
    0.25
     remaining
    0.24
    åı¦ä¸ĢåįĬ
    0.24
     Remaining
    0.24
    Activations Density 0.086%

    No Known Activations