© 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. 33829
    Prev
    Next
    INDEX
    Explanations

    morphological and other morph- prefixes

    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
    nal
    -0.10
    ellig
    -0.10
     popular
    -0.10
    ubs
    -0.09
     Popular
    -0.09
    ç«ĭ
    -0.09
    _diag
    -0.09
    etty
    -0.09
    hood
    -0.09
    aje
    -0.09
    POSITIVE LOGITS
     sle
    0.10
    ologically
    0.09
     itch
    0.09
     susp
    0.09
    ological
    0.08
     chuck
    0.08
    Bloc
    0.08
    ffen
    0.08
     Isles
    0.08
    .metamodel
    0.08
    Activations Density 0.027%

    No Known Activations