© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 6861
    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
    ARI
    -0.08
    --)↵
    -0.08
     fier
    -0.08
     Boiler
    -0.07
     expanding
    -0.07
    eken
    -0.07
     confused
    -0.07
    .online
    -0.07
     Muj
    -0.07
    rij
    -0.07
    POSITIVE LOGITS
    ief
    0.12
     Oswald
    0.11
     periods
    0.11
    Slave
    0.10
     ages
    0.10
    lien
    0.10
    /sl
    0.10
     bert
    0.10
    styl
    0.10
     Arms
    0.10
    Activations Density 0.000%

    No Known Activations