© 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. 26527
    Prev
    Next
    INDEX
    Explanations

    infection, contagion, or mirroring behavior

    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
    sar
    -0.14
     retaining
    -0.11
    Xd
    -0.11
    .yahoo
    -0.10
     sim
    -0.10
    usa
    -0.10
     Willis
    -0.10
     Nickel
    -0.10
    ennie
    -0.10
    ari
    -0.09
    POSITIVE LOGITS
     contagious
    0.27
     contag
    0.24
     infectious
    0.19
     Infect
    0.18
     mirrored
    0.18
     infect
    0.17
     recip
    0.16
     inspiring
    0.16
     vic
    0.16
     mirror
    0.16
    Activations Density 0.120%

    No Known Activations