© 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. 114749
    Prev
    Next
    INDEX
    Explanations

    pharmacy and retail sales

    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
     ETA
    -0.11
     Pistol
    -0.10
     Monetary
    -0.10
     intoxic
    -0.10
     erot
    -0.09
    ots
    -0.09
     ki
    -0.09
     Currency
    -0.09
     treasury
    -0.09
     pistol
    -0.09
    POSITIVE LOGITS
     couch
    0.12
     Couch
    0.12
     upscale
    0.11
     concealed
    0.10
     guise
    0.10
     suburban
    0.10
     sophistication
    0.10
     Skype
    0.10
     disguised
    0.10
     Sofa
    0.10
    Activations Density 0.010%

    No Known Activations