© 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. 58962
    Prev
    Next
    INDEX
    Explanations

    flash memory and capacity

    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
    Negative Logits
     kin
    -0.11
    arms
    -0.10
     MainForm
    -0.10
    Minimal
    -0.10
    control
    -0.09
     jet
    -0.09
     esper
    -0.09
     ladies
    -0.09
     resultant
    -0.09
     Nose
    -0.09
    POSITIVE LOGITS
     interle
    0.09
     backing
    0.08
     tick
    0.08
     volatile
    0.08
     capacities
    0.08
     ticks
    0.08
     write
    0.08
     writable
    0.08
     synchronous
    0.08
    capacity
    0.08
    Activations Density 0.063%

    No Known Activations