© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92538
    Prev
    Next
    INDEX
    Explanations

    social media and networking 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
    Negative Logits
     trophies
    -0.10
     externally
    -0.09
     canon
    -0.09
     negotiated
    -0.08
    /packages
    -0.08
    rang
    -0.08
     Eck
    -0.08
    _TRI
    -0.08
     external
    -0.08
     clit
    -0.08
    POSITIVE LOGITS
     hashtags
    0.16
     networks
    0.16
     Facebook
    0.15
     hashtag
    0.15
     Twitter
    0.15
     social
    0.14
     LinkedIn
    0.13
     networking
    0.13
     communities
    0.13
     facebook
    0.13
    Activations Density 0.003%

    No Known Activations