© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    technical or factual topics

    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
    #Region
    -0.23
    BOSE
    -0.22
    '&&
    -0.21
    /tcp
    -0.20
    IllegalAccessException
    -0.20
    :params
    -0.20
    ertiary
    -0.20
    缸åħ³è´Łè´£
    -0.20
     freopen
    -0.19
    ($('.
    -0.19
    POSITIVE LOGITS
    onestly
    0.22
    å¬
    0.21
    容
    0.21
     ${({
    0.20
    伯
    0.20
    éĿ
    0.20
    istique
    0.19
    lieÃŁ
    0.19
     Voor
    0.19
    elight
    0.18
    Activations Density 0.001%

    No Known Activations