© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8153
    Prev
    Next
    INDEX
    Explanations

    functionality or equality

    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
    Negative Logits
    oli
    -0.08
     encouraging
    -0.08
     Petty
    -0.08
    plet
    -0.08
    fty
    -0.08
     encour
    -0.07
    curr
    -0.07
     cil
    -0.07
    uku
    -0.07
     exciting
    -0.07
    POSITIVE LOGITS
     Prefer
    0.12
     abound
    0.11
    -filled
    0.11
     spiral
    0.11
     Suz
    0.10
    vero
    0.10
     heaps
    0.10
     exe
    0.10
     sow
    0.10
    /screen
    0.10
    Activations Density 0.006%

    No Known Activations