© 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. 5977
    Prev
    Next
    INDEX
    Explanations

    damage to materials

    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
     tamp
    -0.10
     warmed
    -0.09
     replen
    -0.09
     energ
    -0.08
     parcel
    -0.08
     distracted
    -0.07
     unlikely
    -0.07
     parcels
    -0.07
     Pom
    -0.07
     distractions
    -0.07
    POSITIVE LOGITS
     permanently
    0.21
     cracked
    0.19
     cracking
    0.19
     deform
    0.17
     permanent
    0.17
     irreversible
    0.16
     cracks
    0.16
     mold
    0.16
     leak
    0.16
     crack
    0.16
    Activations Density 0.634%

    No Known Activations