© 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. 7660
    Prev
    Next
    INDEX
    Explanations

    brand name, getting things, marrying

    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
    odem
    -0.08
     coincidence
    -0.07
     imitation
    -0.07
     hopefully
    -0.07
     cub
    -0.07
     fingerprint
    -0.07
     preparations
    -0.07
     embarrassing
    -0.07
     readiness
    -0.07
     professionalism
    -0.07
    POSITIVE LOGITS
     effortlessly
    0.21
     attracting
    0.20
     effortless
    0.17
     attract
    0.17
     easily
    0.16
     attracts
    0.16
     Easily
    0.15
     surrounded
    0.14
     everybody
    0.14
     Everywhere
    0.14
    Activations Density 0.044%

    No Known Activations