© 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. 30371
    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
    olo
    -0.12
    ames
    -0.11
     Kes
    -0.10
     Civ
    -0.10
     freak
    -0.09
     Tut
    -0.09
     Nail
    -0.09
     bor
    -0.09
    ream
    -0.09
     embar
    -0.09
    POSITIVE LOGITS
     nond
    0.12
     privile
    0.10
     cach
    0.10
     dorm
    0.10
     detain
    0.10
    ellij
    0.10
     ventilation
    0.09
    pu
    0.09
     Turk
    0.09
     exclus
    0.09
    Activations Density 0.000%

    No Known Activations