© 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. 49169
    Prev
    Next
    INDEX
    Explanations

    connective additive conjunctions

    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
    iser
    -0.10
    ioned
    -0.10
    avan
    -0.10
    ]=>
    -0.10
     lash
    -0.09
    ihan
    -0.09
    reamble
    -0.09
    bb
    -0.09
     fa
    -0.09
    ()=>
    -0.09
    POSITIVE LOGITS
     furthermore
    0.63
     additionally
    0.58
     moreover
    0.57
    Additionally
    0.56
     Also
    0.55
     Additionally
    0.55
    Also
    0.54
     also
    0.52
    Furthermore
    0.51
     Furthermore
    0.50
    Activations Density 1.205%

    No Known Activations