© 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. 49173
    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
     Killer
    -0.10
     Pru
    -0.09
     (@
    -0.09
     Wich
    -0.09
    uez
    -0.08
    Âł
    -0.08
     raced
    -0.08
    lude
    -0.08
     Airbnb
    -0.08
     teamed
    -0.08
    POSITIVE LOGITS
    ows
    0.10
     fet
    0.10
    Reviewed
    0.10
     Fet
    0.09
     aver
    0.09
    isher
    0.09
    ratings
    0.09
    ucz
    0.09
     bondage
    0.09
    arme
    0.09
    Activations Density 0.000%

    No Known Activations