© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16138
    Prev
    Next
    INDEX
    Explanations

    Did you know?

    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
     rightfully
    -0.11
     kra
    -0.10
     fres
    -0.10
    imagin
    -0.10
    ippers
    -0.10
     dizzy
    -0.09
     Coleman
    -0.09
     Baum
    -0.09
    osl
    -0.09
    raud
    -0.09
    POSITIVE LOGITS
     Fact
    0.11
    fact
    0.10
    Fact
    0.10
     âĸº
    0.10
     inventor
    0.10
     UNIVERS
    0.10
     fact
    0.09
     aver
    0.09
     According
    0.09
    rary
    0.09
    Activations Density 0.027%

    No Known Activations