© 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. 29732
    Prev
    Next
    INDEX
    Explanations

    communication and messaging platforms

    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
     validation
    -0.10
     Offensive
    -0.10
     offensive
    -0.09
    thed
    -0.09
     Validation
    -0.09
     Fres
    -0.09
     selfie
    -0.09
     entertainment
    -0.09
     youtube
    -0.09
     Station
    -0.08
    POSITIVE LOGITS
     messaging
    0.25
     chat
    0.22
     communication
    0.20
     Messaging
    0.19
     text
    0.18
    Messaging
    0.18
     texting
    0.18
     channels
    0.17
     messenger
    0.17
     communications
    0.17
    Activations Density 0.406%

    No Known Activations