© 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. 32075
    Prev
    Next
    INDEX
    Explanations

    industrial equipment

    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
     solder
    -0.16
     carpet
    -0.13
    /Home
    -0.12
     Carp
    -0.12
     carp
    -0.12
     countert
    -0.11
     Garmin
    -0.11
     Carpet
    -0.11
     postage
    -0.11
     DIY
    -0.11
    POSITIVE LOGITS
     concrete
    0.18
     gir
    0.18
     Concrete
    0.17
     steel
    0.16
    Concrete
    0.15
     crane
    0.15
     Steel
    0.14
     equipment
    0.14
     tanks
    0.14
    steel
    0.13
    Activations Density 5.006%

    No Known Activations