© 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. 872
    Prev
    Next
    INDEX
    Explanations

    say =

    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
    BuilderInterface
    -0.29
     cornerback
    -0.23
    :border
    -0.23
    .fromFunction
    -0.23
     protester
    -0.22
     paramMap
    -0.22
    -scenes
    -0.22
    =zeros
    -0.22
     misogyn
    -0.22
     misog
    -0.21
    POSITIVE LOGITS
     =
    0.48
     =↵
    0.31
    对çħ§æ£ĢæŁ¥
    0.25
    %);↵
    0.24
     ÑģенÑĤ
    0.23
     =↵↵
    0.23
     =(
    0.23
    ï¼Ŀ
    0.22
     Decompiled
    0.22
    hasOne
    0.22
    Activations Density 0.876%

    No Known Activations