© 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. 116859
    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
     emailing
    -0.12
     cyl
    -0.11
     Whe
    -0.10
     Roc
    -0.10
    ije
    -0.10
    ATUS
    -0.10
     Paula
    -0.10
     Artikel
    -0.09
    /he
    -0.09
    atty
    -0.09
    POSITIVE LOGITS
    /twitter
    0.22
     Twitter
    0.21
     social
    0.20
    Twitter
    0.19
     Instagram
    0.18
    /social
    0.18
     Facebook
    0.17
     platforms
    0.17
    Facebook
    0.16
     twitter
    0.16
    Activations Density 0.071%

    No Known Activations