© 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. 8862
    Prev
    Next
    INDEX
    Explanations

    natural objects and foods

    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
     squirt
    -0.09
     Ents
    -0.08
    abis
    -0.08
     fry
    -0.08
     mach
    -0.08
     SAVE
    -0.08
    ores
    -0.07
    rus
    -0.07
     Ary
    -0.07
     league
    -0.07
    POSITIVE LOGITS
    -like
    0.14
    &e
    0.10
    ,\↵
    0.09
     descendant
    0.08
    -style
    0.08
    -type
    0.08
    ·
    0.08
     bound
    0.08
     Desc
    0.08
     "=",
    0.08
    Activations Density 0.273%

    No Known Activations