© 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. 61876
    Prev
    Next
    INDEX
    Explanations

    alternative / substitute

    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
    ader
    -0.09
    oin
    -0.09
     pipe
    -0.09
     Lloyd
    -0.09
     spont
    -0.08
     contradiction
    -0.08
     granularity
    -0.08
     impro
    -0.08
     contrad
    -0.08
     scant
    -0.08
    POSITIVE LOGITS
     alternatives
    0.22
     alternative
    0.20
     Altern
    0.19
     Alternative
    0.18
     substitutes
    0.17
    Altern
    0.17
     replacements
    0.17
     substitute
    0.15
     alternate
    0.15
    Alternative
    0.15
    Activations Density 0.183%

    No Known Activations