© 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. 4461
    Prev
    Next
    INDEX
    Explanations

    metaphor or analogy

    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
     Infos
    -0.09
     retire
    -0.09
    hints
    -0.09
    385
    -0.09
    åĥı
    -0.08
    fel
    -0.08
     Frontier
    -0.08
    ECT
    -0.08
     HIP
    -0.08
     trail
    -0.08
    POSITIVE LOGITS
     analogy
    0.12
     metaphor
    0.09
    abin
    0.09
     bib
    0.09
     Gar
    0.09
     alleg
    0.09
    urgence
    0.08
     paradigm
    0.08
    berra
    0.08
    gid
    0.08
    Activations Density 0.205%

    No Known Activations