© 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. 33347
    Prev
    Next
    INDEX
    Explanations

    online purchase

    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
     ****
    -0.10
     succes
    -0.09
    ÃĤ
    -0.09
    .."
    -0.09
     exploited
    -0.08
     famously
    -0.08
    âĢ¦"
    -0.08
     churn
    -0.08
     *****
    -0.08
     prt
    -0.08
    POSITIVE LOGITS
     buy
    0.23
     Buy
    0.22
     cheapest
    0.20
     Order
    0.19
     soma
    0.18
     order
    0.18
     Cheap
    0.18
     purchase
    0.17
     Purchase
    0.17
     Want
    0.16
    Activations Density 0.122%

    No Known Activations