© 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. 5807
    Prev
    Next
    INDEX
    Explanations

    settle differences or make decisions

    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
     indefinite
    -0.11
    ally
    -0.11
    nage
    -0.11
    rete
    -0.10
    es
    -0.09
    like
    -0.09
     dangling
    -0.09
    kode
    -0.09
     setups
    -0.09
    liest
    -0.09
    POSITIVE LOGITS
     down
    0.12
     disputes
    0.12
    -down
    0.11
     accounts
    0.09
     into
    0.09
     dust
    0.09
     Fairfield
    0.09
     disagreements
    0.09
    562
    0.08
    deg
    0.08
    Activations Density 0.008%

    No Known Activations