© 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. 90780
    Prev
    Next
    INDEX
    Explanations

    social events and gatherings

    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
     Tit
    -0.10
     reference
    -0.08
    -linked
    -0.08
     Ritual
    -0.08
     mornings
    -0.08
    Tit
    -0.08
    activ
    -0.08
     Hag
    -0.08
    _ta
    -0.08
     tot
    -0.08
    POSITIVE LOGITS
     party
    0.19
     parties
    0.16
    party
    0.15
    -party
    0.15
    .party
    0.13
    _party
    0.13
     Parties
    0.12
    Party
    0.12
     Party
    0.12
     PARTY
    0.12
    Activations Density 0.077%

    No Known Activations