© 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. 6815
    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
    Shortcut
    -0.10
    eki
    -0.09
     Towers
    -0.08
     tightened
    -0.08
    .pt
    -0.08
     McCarthy
    -0.08
     notices
    -0.08
     ranger
    -0.08
     goose
    -0.08
    ector
    -0.08
    POSITIVE LOGITS
     wast
    0.09
     tent
    0.09
    shal
    0.09
     Cour
    0.09
     cap
    0.08
     Neb
    0.08
    isch
    0.08
    /pr
    0.08
     sidel
    0.08
     shovel
    0.08
    Activations Density 0.000%

    No Known Activations