© 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. 28183
    Prev
    Next
    INDEX
    Explanations

    social media 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
     bach
    -0.10
    usb
    -0.10
     matlab
    -0.10
     locksmith
    -0.10
     lingerie
    -0.10
     escorts
    -0.09
     barg
    -0.09
     listings
    -0.09
    emma
    -0.09
     spotting
    -0.09
    POSITIVE LOGITS
     social
    0.33
    social
    0.27
     Social
    0.26
     Facebook
    0.26
     SOCIAL
    0.25
    /social
    0.25
    -social
    0.25
    Social
    0.24
     platforms
    0.23
    Facebook
    0.22
    Activations Density 0.488%

    No Known Activations