© 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. 57948
    Prev
    Next
    INDEX
    Explanations

    goodbye-like 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
    ekt
    -0.11
    loop
    -0.09
    kt
    -0.09
     Station
    -0.08
     Sag
    -0.08
    .cgi
    -0.08
     hans
    -0.08
    .Report
    -0.08
    Station
    -0.08
    ify
    -0.08
    POSITIVE LOGITS
     lan
    0.09
    hay
    0.09
    rna
    0.09
     Charg
    0.08
    peech
    0.08
     frank
    0.08
    zem
    0.08
    itch
    0.08
    .openg
    0.08
    rases
    0.08
    Activations Density 0.007%

    No Known Activations