© 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. 7284
    Prev
    Next
    INDEX
    Explanations

    have conversations

    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
     setback
    -0.10
     conduc
    -0.10
     resp
    -0.10
     comport
    -0.09
     Invitation
    -0.09
     LAP
    -0.09
     raft
    -0.09
    tie
    -0.09
     Mara
    -0.09
    iste
    -0.08
    POSITIVE LOGITS
     conversations
    0.30
     conversation
    0.28
    conversation
    0.20
     discussions
    0.20
     Conversation
    0.19
     dialogue
    0.19
     debates
    0.18
     Convers
    0.18
     dialog
    0.17
     dialogs
    0.17
    Activations Density 0.022%

    No Known Activations