© 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. 29733
    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
    ajo
    -0.11
     Aid
    -0.10
     aid
    -0.10
    534
    -0.09
     aide
    -0.09
     ITE
    -0.09
     min
    -0.08
    erk
    -0.08
    734
    -0.08
    isi
    -0.08
    POSITIVE LOGITS
    alion
    0.12
     reco
    0.10
    anmar
    0.10
    oter
    0.10
    roe
    0.10
     unb
    0.10
     locks
    0.10
     pared
    0.10
     capped
    0.09
    -medium
    0.09
    Activations Density 0.000%

    No Known Activations