© 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. 31158
    Prev
    Next
    INDEX
    Explanations

    population or populace

    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
     Gew
    -0.09
    ect
    -0.09
     outr
    -0.08
    etz
    -0.08
     Pero
    -0.08
    emann
    -0.08
    edes
    -0.08
    hq
    -0.08
    æĭ
    -0.08
    ault
    -0.08
    POSITIVE LOGITS
     population
    0.14
     Population
    0.11
     populace
    0.10
    population
    0.10
     Links
    0.10
     populations
    0.10
     electorate
    0.09
    Population
    0.09
    ernet
    0.09
     graduating
    0.09
    Activations Density 0.028%

    No Known Activations