© 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. 5246
    Prev
    Next
    INDEX
    Explanations

    major reasons or purposes

    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
     gossip
    -0.10
    /do
    -0.10
     launder
    -0.10
     incons
    -0.09
     pensions
    -0.09
    Bindings
    -0.09
    PF
    -0.09
    Interop
    -0.09
    erguson
    -0.09
    uez
    -0.09
    POSITIVE LOGITS
     countries
    0.13
     reasons
    0.11
     purposes
    0.11
     regard
    0.11
     reason
    0.10
     sake
    0.10
     case
    0.10
     cases
    0.10
    reason
    0.10
     major
    0.10
    Activations Density 0.013%

    No Known Activations