© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    specific terms

    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
    2
    -0.30
    1
    -0.30
    0
    -0.30
    3
    -0.30
    4
    -0.28
    7
    -0.25
    6
    -0.25
     lineback
    -0.25
    5
    -0.24
     consect
    -0.24
    POSITIVE LOGITS
    ,DB
    0.32
     (*((
    0.32
    -ln
    0.30
    /↵↵↵↵
    0.30
     )↵↵↵↵↵↵↵↵
    0.29
    :;"
    0.28
    åħ¶ä»ĸçļĦ
    0.28
    [".
    0.27
    ————————————————
    0.27
    ;base
    0.27
    Activations Density 7.852%

    No Known Activations