© 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. 45764
    Prev
    Next
    INDEX
    Explanations

    artificially advanced things

    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
    åħįéĻ¤
    -0.22
    éĴ´
    -0.19
     AppBundle
    -0.19
    ery
    -0.19
     SLOT
    -0.18
    派人
    -0.18
    主義
    -0.18
    Ex
    -0.18
     EXEMPLARY
    -0.18
    ism
    -0.18
    POSITIVE LOGITS
    @student
    0.29
    antaged
    0.25
    __);
    0.25
    :normal
    0.24
    egov
    0.24
    /Dk
    0.23
    isoft
    0.23
    apsed
    0.23
    URLException
    0.22
    _Il
    0.22
    Activations Density 0.230%

    No Known Activations