© 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. 113857
    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
     accordingly
    -0.12
     Occup
    -0.10
    gue
    -0.10
     Honest
    -0.09
    ipt
    -0.09
     marking
    -0.09
     lik
    -0.09
    undo
    -0.09
     lay
    -0.09
    Frozen
    -0.09
    POSITIVE LOGITS
     benign
    0.09
     crude
    0.09
    VS
    0.09
    eka
    0.09
    tere
    0.08
     heir
    0.08
     Moj
    0.08
    -volume
    0.08
     prem
    0.08
     Experiment
    0.08
    Activations Density 0.000%

    No Known Activations