© 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. 114082
    Prev
    Next
    INDEX
    Explanations

    buy

    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
     greeted
    -0.10
    zza
    -0.10
     Cove
    -0.10
     proceeded
    -0.10
    hon
    -0.09
     arrived
    -0.09
    emann
    -0.09
     pii
    -0.09
     Kov
    -0.09
     sustained
    -0.09
    POSITIVE LOGITS
     buy
    0.12
     Buy
    0.11
     buying
    0.11
     purch
    0.11
     buys
    0.10
     procure
    0.10
     safest
    0.10
    buy
    0.10
    ver
    0.10
     purchase
    0.09
    Activations Density 0.001%

    No Known Activations