© 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. 113001
    Prev
    Next
    INDEX
    Explanations

    apply to", "mathematical", "rotation more", "commit", "committed", "intens", "rine", "neural"

    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
    iek
    -0.11
    alach
    -0.10
    kah
    -0.10
    agus
    -0.09
    uchar
    -0.09
     Harvey
    -0.09
    //}}
    -0.09
    hest
    -0.09
     Sas
    -0.09
    onga
    -0.09
    POSITIVE LOGITS
     intens
    0.10
    achten
    0.09
     commitment
    0.09
     commit
    0.09
     bang
    0.08
    rine
    0.08
     committed
    0.08
    -Tr
    0.08
    uib
    0.08
    enne
    0.08
    Activations Density 0.001%

    No Known Activations