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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 955
    Prev
    Next
    INDEX
    Explanations

    period

    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
    快讯
    -0.19
    UFACT
    -0.19
    .getField
    -0.18
    Äħd
    -0.18
    æ°
    -0.18
     RV
    -0.18
    .bitmap
    -0.18
    缸åħ³æĸ°éĹ»
    -0.18
     ult
    -0.17
    (arc
    -0.17
    POSITIVE LOGITS
    TOTYPE
    0.25
     Clintons
    0.24
    -scenes
    0.23
    gnore
    0.23
    }elseif
    0.21
     rencont
    0.21
    <?↵
    0.21
    =@"
    0.21
    :\/\/
    0.20
    ẩu
    0.20
    Activations Density 1.081%

    No Known Activations