© 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. 49500
    Prev
    Next
    INDEX
    Explanations

    dialogue or conversation exchanges

    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
     halfway
    -0.10
     indefinite
    -0.10
     lavish
    -0.09
     indiscrim
    -0.09
     vir
    -0.09
     sleeping
    -0.09
     unify
    -0.09
     binge
    -0.09
     sleeps
    -0.09
     Contents
    -0.09
    POSITIVE LOGITS
     conversation
    0.37
     dialogue
    0.35
     exchanges
    0.33
     exchange
    0.32
     conversations
    0.30
     dialog
    0.29
     Conversation
    0.28
     exchanged
    0.28
     interaction
    0.28
    Conversation
    0.28
    Activations Density 0.304%

    No Known Activations