© 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. 33458
    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
     Gale
    -0.08
     tol
    -0.07
    ú
    -0.07
     mono
    -0.07
    rai
    -0.07
     Ingen
    -0.07
     Century
    -0.07
     barrier
    -0.07
     ruth
    -0.07
    enko
    -0.07
    POSITIVE LOGITS
    yb
    0.11
     Portal
    0.11
     Slee
    0.11
    faker
    0.11
    Portal
    0.10
    ecz
    0.10
    tips
    0.10
     Alam
    0.10
    spr
    0.10
    à¹Ī
    0.10
    Activations Density 0.000%

    No Known Activations