© 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. 49795
    Prev
    Next
    INDEX
    Explanations

    real estate lease terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     intimately
    -0.10
    onet
    -0.10
    rant
    -0.09
     simultaneously
    -0.09
    enant
    -0.09
    ness
    -0.09
     Sas
    -0.09
     gadget
    -0.08
    cape
    -0.08
     hairy
    -0.08
    POSITIVE LOGITS
    Bes
    0.09
    ä¿
    0.09
     Plains
    0.09
     Blaze
    0.09
    -su
    0.09
     Dies
    0.09
     cub
    0.09
     Bes
    0.08
    lid
    0.08
     Bridge
    0.08
    Activations Density 0.001%

    No Known Activations