© 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. 46726
    Prev
    Next
    INDEX
    Explanations

    information

    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
    comed
    -0.25
    é¾ĥ
    -0.25
    iferay
    -0.22
    toi
    -0.21
    "h
    -0.21
     Während
    -0.21
    :numel
    -0.21
    _REFER
    -0.21
    åħ¨èµĦåŃIJ
    -0.21
     Unblock
    -0.20
    POSITIVE LOGITS
    oplevel
    0.22
     FactoryBot
    0.21
     Every
    0.20
    æijĩ头
    0.19
    possibly
    0.19
     every
    0.19
    +'_
    0.19
    event
    0.19
     Haram
    0.19
    arrants
    0.18
    Activations Density 0.065%

    No Known Activations