© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1444
    Prev
    Next
    INDEX
    Explanations

    start or beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pct
    -0.10
    avanaugh
    -0.10
    ÅĦ
    -0.09
    /animations
    -0.09
     Serv
    -0.09
     èĭ
    -0.09
     Valentine
    -0.08
    /graph
    -0.08
     wives
    -0.08
    	finally
    -0.08
    POSITIVE LOGITS
    /start
    0.19
     initial
    0.14
    /init
    0.12
    -stage
    0.12
    (initial
    0.11
    -start
    0.11
     Initial
    0.11
    /welcome
    0.11
    ë¶Ģ
    0.11
     initially
    0.11
    Activations Density 2.772%

    No Known Activations