© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2050
    Prev
    Next
    INDEX
    Explanations

    increasingly, progressively, decreasing, until

    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
     enough
    -0.09
    onte
    -0.09
    izen
    -0.09
     sufficiently
    -0.08
    unda
    -0.08
    lem
    -0.08
    pite
    -0.08
     Sage
    -0.08
     Snyder
    -0.08
     completely
    -0.08
    POSITIVE LOGITS
     increasingly
    0.19
     progressively
    0.17
     until
    0.16
     increasing
    0.15
    until
    0.14
     decreasing
    0.14
     till
    0.13
     Until
    0.12
     Increasing
    0.12
    Until
    0.11
    Activations Density 0.271%

    No Known Activations