© 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. 116275
    Prev
    Next
    INDEX
    Explanations

    communication channels

    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
     chairs
    -0.12
     chair
    -0.08
     Chair
    -0.08
     Chairs
    -0.08
     hat
    -0.07
     weeds
    -0.07
     Stanford
    -0.07
    -chair
    -0.07
     childbirth
    -0.07
    Chair
    -0.07
    POSITIVE LOGITS
     forums
    0.15
     emailing
    0.15
     Forums
    0.14
     emails
    0.14
     mailing
    0.14
     email
    0.14
    forums
    0.13
     messaging
    0.13
     bulletin
    0.13
     texting
    0.13
    Activations Density 0.259%

    No Known Activations