© 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. 46837
    Prev
    Next
    INDEX
    Explanations

    allow

    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
    unt
    -0.11
    ether
    -0.10
     nak
    -0.09
     ado
    -0.09
     Wid
    -0.09
     declining
    -0.09
     Farrell
    -0.09
    wed
    -0.08
     eid
    -0.08
     Paran
    -0.08
    POSITIVE LOGITS
     happen
    0.10
    feat
    0.10
     participation
    0.10
     Weiss
    0.10
     comparisons
    0.09
     interaction
    0.09
     exploration
    0.09
     purchases
    0.09
     Fior
    0.09
     flourish
    0.09
    Activations Density 0.360%

    No Known Activations