© 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. 15538
    Prev
    Next
    INDEX
    Explanations

    synchronized, in concert, parallel, relation

    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
     interaction
    -0.07
     interactions
    -0.07
     fier
    -0.07
     sto
    -0.06
     Zug
    -0.06
    866
    -0.06
     ram
    -0.06
    atha
    -0.06
     erotica
    -0.06
     intimate
    -0.06
    POSITIVE LOGITS
     Kron
    0.11
    omat
    0.11
    idders
    0.11
    Solo
    0.11
     recurring
    0.11
     segmented
    0.11
     lobbyist
    0.11
    ward
    0.11
    omal
    0.10
     heaps
    0.10
    Activations Density 0.001%

    No Known Activations