© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90243
    Prev
    Next
    INDEX
    Explanations

    em bedded scientific terms

    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
     civilian
    -0.10
     outsiders
    -0.09
     outside
    -0.09
     civilians
    -0.09
     worldly
    -0.08
     NON
    -0.08
     exterior
    -0.08
    rita
    -0.08
     mange
    -0.08
    outside
    -0.08
    POSITIVE LOGITS
     errno
    0.10
     GREEN
    0.10
     concessions
    0.10
    bote
    0.09
     Twice
    0.09
    ialized
    0.09
    ãĢľ
    0.09
     polic
    0.09
    ptest
    0.09
     Edwin
    0.09
    Activations Density 2.160%

    No Known Activations