© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89371
    Prev
    Next
    INDEX
    Explanations

    first names followed by last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emil
    -0.10
     Wyn
    -0.08
     Osw
    -0.08
     Esther
    -0.08
     Cecil
    -0.08
     Papa
    -0.07
     lacking
    -0.07
     Altern
    -0.07
     Eug
    -0.07
     dissect
    -0.07
    POSITIVE LOGITS
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    0.10
    ·¸
    0.10
     Probe
    0.09
    orage
    0.09
     Fields
    0.09
     Green
    0.09
    .Metro
    0.09
    Cart
    0.09
     GREEN
    0.09
     smith
    0.09
    Activations Density 0.366%

    No Known Activations