© 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. 26471
    Prev
    Next
    INDEX
    Explanations

    party or similar events

    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
     Dek
    -0.08
     Ned
    -0.08
    otten
    -0.08
     lasc
    -0.08
     vulnerability
    -0.08
     merc
    -0.08
     proudly
    -0.08
     insol
    -0.08
     Twe
    -0.08
    ploy
    -0.08
    POSITIVE LOGITS
     party
    0.39
     parties
    0.32
    party
    0.30
    -party
    0.28
     PARTY
    0.28
     Party
    0.26
    Party
    0.26
     Parties
    0.23
    .party
    0.21
    _party
    0.21
    Activations Density 0.071%

    No Known Activations