© 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. 114438
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ITES
    -0.12
    aside
    -0.12
    gregated
    -0.12
    -chan
    -0.12
    unfinished
    -0.11
     Finished
    -0.11
    elves
    -0.11
    gaard
    -0.11
    usp
    -0.11
    apos
    -0.11
    POSITIVE LOGITS
    ed
    0.10
     replen
    0.09
     strat
    0.08
     Bul
    0.07
     Strat
    0.07
     Bucc
    0.07
    abl
    0.07
     shape
    0.07
     culture
    0.07
    (xx
    0.07
    Activations Density 0.000%

    No Known Activations