© 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. 31299
    Prev
    Next
    INDEX
    Explanations

    geological survey sedimentary ocean island

    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
     extrad
    -0.09
     landmarks
    -0.09
     prost
    -0.09
     mating
    -0.08
     gilt
    -0.08
     catapult
    -0.08
     bers
    -0.08
     territories
    -0.08
     incapac
    -0.08
     exhaust
    -0.08
    POSITIVE LOGITS
     Geological
    0.28
     geological
    0.26
     geo
    0.24
     ge
    0.24
     lith
    0.23
     Geo
    0.23
    Geo
    0.22
     geom
    0.22
     sediment
    0.21
     reconnaissance
    0.20
    Activations Density 4.368%

    No Known Activations