© 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. 7024
    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
     day
    -0.09
    atron
    -0.09
    reich
    -0.08
     fray
    -0.08
     Fib
    -0.08
     yours
    -0.08
     reconsider
    -0.08
     Imper
    -0.08
     dej
    -0.08
     dig
    -0.08
    POSITIVE LOGITS
     spr
    0.10
     clandest
    0.10
     ministries
    0.10
     lucrative
    0.10
    spr
    0.10
    Hooks
    0.09
     nom
    0.09
     shady
    0.09
    efs
    0.09
     glimpse
    0.09
    Activations Density 0.000%

    No Known Activations