© 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. 33213
    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
     presum
    -0.08
    —or
    -0.07
     Spart
    -0.07
    immel
    -0.07
     noisy
    -0.07
     fingerprint
    -0.07
     retarded
    -0.07
     Buddy
    -0.07
     armored
    -0.07
     yap
    -0.06
    POSITIVE LOGITS
    foods
    0.11
    kon
    0.11
    roe
    0.11
     Chan
    0.11
     warrant
    0.10
    ypad
    0.10
     Loose
    0.10
    dbus
    0.10
     gw
    0.10
    /path
    0.10
    Activations Density 0.000%

    No Known Activations