© 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. 3348
    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
     lineman
    -0.22
     relu
    -0.20
    ipy
    -0.20
     cornerback
    -0.20
    iplinary
    -0.19
    nt
    -0.19
    TreeWidgetItem
    -0.19
    iasm
    -0.19
    setLayout
    -0.19
     áll
    -0.18
    POSITIVE LOGITS
    InMillis
    0.28
    okit
    0.24
    auga
    0.24
    çĭŀ
    0.23
    arness
    0.22
    ardu
    0.22
    isclosed
    0.21
    agini
    0.20
    lectic
    0.20
    ecided
    0.20
    Activations Density 0.244%

    No Known Activations