© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    physical characteristics and properties

    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
     Bris
    -0.08
    aison
    -0.08
    ADA
    -0.08
     practise
    -0.08
    Rpc
    -0.08
     Jess
    -0.08
    .Web
    -0.08
     Rhe
    -0.08
     Rousse
    -0.07
    value
    -0.07
    POSITIVE LOGITS
    ity
    0.11
    s
    0.10
    -location
    0.09
     location
    0.09
    /em
    0.09
    tics
    0.09
    Äĩe
    0.09
    ities
    0.09
     physical
    0.08
    CB
    0.08
    Activations Density 0.098%

    No Known Activations