© 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. 15297
    Prev
    Next
    INDEX
    Explanations

    communication and its contexts

    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
    bie
    -0.09
    igh
    -0.09
    Speak
    -0.09
    lok
    -0.09
    algo
    -0.09
    unker
    -0.09
    quette
    -0.09
    holm
    -0.09
    alen
    -0.09
    ignite
    -0.09
    POSITIVE LOGITS
     channels
    0.15
     breakdown
    0.14
     skills
    0.13
    UNICATION
    0.12
     Channels
    0.12
     between
    0.11
     channel
    0.11
    channels
    0.11
     mediums
    0.11
    unication
    0.11
    Activations Density 0.077%

    No Known Activations