© 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. 18123
    Prev
    Next
    INDEX
    Explanations

    flags

    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
     bench
    -0.12
     Hera
    -0.11
    illus
    -0.10
     Scri
    -0.09
     Models
    -0.09
    Models
    -0.09
     corridor
    -0.09
     couch
    -0.09
     models
    -0.09
     circuits
    -0.09
    POSITIVE LOGITS
     flag
    0.30
     flags
    0.29
     sails
    0.26
     Flag
    0.25
    flag
    0.24
     mast
    0.23
    -flag
    0.23
     sail
    0.23
    flags
    0.22
     Flags
    0.22
    Activations Density 0.155%

    No Known Activations