© 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. 49663
    Prev
    Next
    INDEX
    Explanations

    specific domains

    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
     Stub
    -0.11
    Bro
    -0.10
     Death
    -0.10
     reck
    -0.09
    PJ
    -0.09
    genes
    -0.09
     courtesy
    -0.09
    .Binding
    -0.09
    Stub
    -0.09
    .rev
    -0.09
    POSITIVE LOGITS
     exclusively
    0.11
     alone
    0.10
     specifically
    0.10
    iqu
    0.10
     explicitly
    0.10
    alone
    0.10
    yo
    0.09
    936
    0.09
    ë§Į
    0.09
    ↵                    ↵
    0.09
    Activations Density 0.221%

    No Known Activations