© 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-CHAT-65K
    7. 45765
    Prev
    Next
    INDEX
    Explanations

    text content

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¹¢
    -0.21
    indow
    -0.20
     rall
    -0.19
    deserialize
    -0.18
    _codigo
    -0.18
     paraph
    -0.18
    phin
    -0.18
    orget
    -0.18
    nbr
    -0.18
    å¼ķ
    -0.18
    POSITIVE LOGITS
    .UIManager
    0.24
    åĢļ
    0.22
    crollView
    0.21
    irlines
    0.20
    (<?
    0.20
    .ToShort
    0.19
    istringstream
    0.19
     ÑģÑĢав
    0.19
    .CreateTable
    0.18
    .SwingConstants
    0.18
    Activations Density 0.009%

    No Known Activations