© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31644
    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
     Lub
    -0.10
     Suppress
    -0.09
     sund
    -0.09
    Suppress
    -0.08
     flattering
    -0.08
     minded
    -0.08
     lub
    -0.07
     Locked
    -0.07
    styl
    -0.07
    ô
    -0.07
    POSITIVE LOGITS
    -short
    0.11
     inher
    0.11
     teenagers
    0.10
     teenager
    0.10
     Carpenter
    0.10
    rels
    0.10
    .tex
    0.10
    rush
    0.10
     mature
    0.10
    -shift
    0.10
    Activations Density 0.000%

    No Known Activations