© 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. 26063
    Prev
    Next
    INDEX
    Explanations

    romance and relationships

    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
     Bomb
    -0.09
    Bomb
    -0.08
     Atkins
    -0.08
     august
    -0.07
     brave
    -0.07
     Petro
    -0.07
     Planned
    -0.07
     jag
    -0.07
     Pir
    -0.07
    igua
    -0.07
    POSITIVE LOGITS
     Romantic
    0.12
     Romance
    0.12
     romantic
    0.11
     romance
    0.11
     Mare
    0.10
    اس
    0.10
    tern
    0.10
     respiratory
    0.10
    ofi
    0.10
    ych
    0.10
    Activations Density 0.003%

    No Known Activations