© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2405
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by words

    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
    whatever
    -0.10
     whoever
    -0.10
     whichever
    -0.10
     whatever
    -0.09
     everything
    -0.09
     Dah
    -0.09
    everything
    -0.09
     progressively
    -0.08
     exactly
    -0.08
    what
    -0.08
    POSITIVE LOGITS
     slightest
    0.11
    .vn
    0.10
     evid
    0.10
     statistic
    0.10
     Advertisement
    0.10
    READY
    0.10
     Entire
    0.10
     respective
    0.10
     sciences
    0.09
    IPP
    0.09
    Activations Density 0.877%

    No Known Activations