© 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. 25956
    Prev
    Next
    INDEX
    Explanations

    aerial photography

    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
     coarse
    -0.10
     segregated
    -0.10
     Medieval
    -0.10
     esto
    -0.09
    ustain
    -0.09
     declines
    -0.09
     etiqu
    -0.09
    idel
    -0.09
    heck
    -0.09
     feudal
    -0.09
    POSITIVE LOGITS
     Abed
    0.11
    /ph
    0.11
     Cyrus
    0.11
     balloon
    0.10
    Longitude
    0.10
     Fix
    0.10
     Alibaba
    0.10
     Mongolia
    0.10
     longitude
    0.10
     Asian
    0.10
    Activations Density 0.067%

    No Known Activations