© 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. 4910
    Prev
    Next
    INDEX
    Explanations

    places that house things

    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
     surroundings
    -0.09
     Warn
    -0.09
     onstage
    -0.08
     surrounding
    -0.08
    EF
    -0.08
     nearby
    -0.07
     Unity
    -0.07
     premises
    -0.07
    izia
    -0.07
     upstairs
    -0.07
    POSITIVE LOGITS
     Concent
    0.10
     concentrated
    0.10
     Where
    0.09
    Where
    0.09
     concentr
    0.09
     stash
    0.09
     nostra
    0.09
     onde
    0.09
     concentrate
    0.09
     Qual
    0.09
    Activations Density 0.388%

    No Known Activations