© 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. 32688
    Prev
    Next
    INDEX
    Explanations

    many people

    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
    Uri
    -0.11
    ka
    -0.10
     unic
    -0.09
    ngo
    -0.09
    ROI
    -0.09
    Own
    -0.09
    /activity
    -0.09
    Trad
    -0.09
     cont
    -0.09
    Aws
    -0.09
    POSITIVE LOGITS
     quarters
    0.10
     unfortunate
    0.10
    /all
    0.10
     fortunate
    0.09
     aspects
    0.09
     shutter
    0.09
     extents
    0.09
     people
    0.08
    (not
    0.08
     marks
    0.08
    Activations Density 0.088%

    No Known Activations