© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48478
    Prev
    Next
    INDEX
    Explanations

    romantic pursuits

    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
     Santana
    -0.09
    olley
    -0.08
    STA
    -0.08
     Mast
    -0.08
    iors
    -0.08
     softly
    -0.08
    ultimate
    -0.07
    Requests
    -0.07
     approximate
    -0.07
    afia
    -0.07
    POSITIVE LOGITS
    ism
    0.14
     incl
    0.13
    ized
    0.13
     invol
    0.13
     interest
    0.11
     involvement
    0.11
     pursuits
    0.11
     endeavors
    0.11
     ende
    0.11
     Ende
    0.11
    Activations Density 0.008%

    No Known Activations