© 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. 14823
    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
     Cru
    -0.11
     Meth
    -0.10
    ront
    -0.10
     Tos
    -0.10
     Duo
    -0.10
    icens
    -0.10
    erra
    -0.10
     Hess
    -0.09
     Frontier
    -0.09
     radios
    -0.09
    POSITIVE LOGITS
     Barnett
    0.09
     reim
    0.09
    arn
    0.09
    ilater
    0.09
     straw
    0.08
    lus
    0.08
     seaw
    0.08
     mun
    0.08
     overtime
    0.08
    oney
    0.08
    Activations Density 0.000%

    No Known Activations