© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55180
    Prev
    Next
    INDEX
    Explanations

    analogy and parallels

    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
    ventas
    -0.09
    pha
    -0.09
     ampl
    -0.09
    arker
    -0.09
     incumb
    -0.09
     Swing
    -0.09
     dev
    -0.08
     Everywhere
    -0.08
    omit
    -0.08
     catal
    -0.08
    POSITIVE LOGITS
     analogy
    0.21
     analogous
    0.20
     treating
    0.18
     akin
    0.17
     treat
    0.17
     parallels
    0.16
     treated
    0.15
     liken
    0.15
     analog
    0.15
     resemble
    0.15
    Activations Density 0.199%

    No Known Activations