© 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. 2805
    Prev
    Next
    INDEX
    Explanations

    UI list items

    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
    /Branch
    -0.25
     )}↵↵
    -0.23
    é»ijæģ¶
    -0.20
    IDEOS
    -0.19
    "nil
    -0.19
    ãĤ¸ãĤ§
    -0.19
    å¹´çĶ±
    -0.19
    åįĩéĻį
    -0.18
    :maj
    -0.18
    rootScope
    -0.18
    POSITIVE LOGITS
     DataRow
    0.27
    <article
    0.27
     individually
    0.24
    DataRow
    0.24
    çĺ°
    0.24
     individual
    0.23
     each
    0.23
    ListItem
    0.23
     row
    0.22
     ListTile
    0.22
    Activations Density 0.702%

    No Known Activations