© 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. 113751
    Prev
    Next
    INDEX
    Explanations

    TheNetworksToSixAbItIPCPUItThese

    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
     meanwhile
    -0.09
     sinon
    -0.08
    Entries
    -0.08
    OMEM
    -0.08
     bins
    -0.08
     crow
    -0.08
     doubly
    -0.08
    trainer
    -0.08
     bus
    -0.08
     Doub
    -0.08
    POSITIVE LOGITS
    itch
    0.11
    ATTR
    0.10
     pier
    0.10
     attraction
    0.10
     subconscious
    0.10
     Researchers
    0.10
     Studies
    0.10
     Cup
    0.10
     strongest
    0.10
     Minute
    0.10
    Activations Density 0.022%

    No Known Activations