© 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. 47299
    Prev
    Next
    INDEX
    Explanations

    warranty and returns

    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
    uras
    -0.10
    lok
    -0.10
     ventures
    -0.09
    linger
    -0.09
    verb
    -0.09
     supper
    -0.09
     dinner
    -0.09
     strip
    -0.09
    ister
    -0.09
     prem
    -0.09
    POSITIVE LOGITS
     repairs
    0.15
     defective
    0.15
     warranty
    0.15
     repairing
    0.13
     repaired
    0.13
     repair
    0.13
     warranties
    0.12
     refunds
    0.12
     refund
    0.12
     defects
    0.12
    Activations Density 0.001%

    No Known Activations