© 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. 89337
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

    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
     suff
    -0.09
     trenches
    -0.09
     overpower
    -0.08
    olis
    -0.08
     hon
    -0.08
     wed
    -0.08
     dram
    -0.08
    agraph
    -0.08
     mates
    -0.08
    annt
    -0.08
    POSITIVE LOGITS
     Dok
    0.10
     facil
    0.09
     Neb
    0.09
     pom
    0.09
     Gomez
    0.09
     sore
    0.09
     zap
    0.09
     Shame
    0.09
     Bearing
    0.09
    Facade
    0.09
    Activations Density 0.191%

    No Known Activations