© 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. 50478
    Prev
    Next
    INDEX
    Explanations

    warranty

    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
    olist
    -0.10
     pinch
    -0.09
     Spoon
    -0.09
     Preview
    -0.09
     borrow
    -0.09
    ietf
    -0.09
    -preview
    -0.09
     crunch
    -0.09
     outr
    -0.09
     susp
    -0.09
    POSITIVE LOGITS
     warranty
    0.40
     Warranty
    0.35
     warranties
    0.29
     firmware
    0.28
     WARRANTY
    0.26
     Firmware
    0.26
    arranty
    0.25
     factory
    0.22
     repair
    0.21
     manufacturer
    0.20
    Activations Density 0.716%

    No Known Activations