© 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. 4757
    Prev
    Next
    INDEX
    Explanations

    rare, unique, original items

    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
     litter
    -0.09
    dock
    -0.08
     Cursor
    -0.08
    iro
    -0.08
    Reviews
    -0.08
    mode
    -0.08
     constructs
    -0.08
    mes
    -0.08
     designing
    -0.08
     retro
    -0.07
    POSITIVE LOGITS
     rare
    0.20
     rarity
    0.18
     Rare
    0.14
     intact
    0.13
    Rare
    0.13
     Rarity
    0.13
     unrest
    0.13
     specimen
    0.11
     belonged
    0.11
     donated
    0.11
    Activations Density 0.455%

    No Known Activations