© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2966
    Prev
    Next
    INDEX
    Explanations

    periods of change or revolution

    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
     increasingly
    -0.11
    ables
    -0.09
     evolving
    -0.09
    zer
    -0.09
     Huff
    -0.08
     disput
    -0.08
    enta
    -0.08
     Mehr
    -0.08
     Constit
    -0.08
     Gallagher
    -0.08
    POSITIVE LOGITS
     period
    0.13
     wave
    0.11
     periods
    0.10
    eca
    0.10
     movement
    0.10
     Period
    0.10
    Period
    0.10
     amor
    0.09
    cul
    0.09
    -period
    0.09
    Activations Density 0.329%

    No Known Activations