© 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. 56077
    Prev
    Next
    INDEX
    Explanations

    after consequence

    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
    enu
    -0.10
    émon
    -0.09
    erot
    -0.09
    isin
    -0.09
    datal
    -0.09
     Cary
    -0.09
     lungs
    -0.08
     integ
    -0.08
     HUD
    -0.08
    رÙĪ
    -0.08
    POSITIVE LOGITS
     subsequent
    0.15
     ensuing
    0.11
     consequ
    0.10
     aftermath
    0.10
     afterward
    0.09
     meetings
    0.09
     afterwards
    0.09
     thereafter
    0.09
     resultant
    0.09
     childbirth
    0.08
    Activations Density 0.168%

    No Known Activations