© 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. 46814
    Prev
    Next
    INDEX
    Explanations

    visits and reunions

    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
     tri
    -0.13
     politely
    -0.11
     gloss
    -0.11
     duo
    -0.10
    osa
    -0.10
    bet
    -0.10
     scam
    -0.10
     triples
    -0.10
    party
    -0.10
     ostr
    -0.10
    POSITIVE LOGITS
     kisses
    0.13
     cudd
    0.13
     kiss
    0.12
     visiting
    0.12
     visit
    0.12
     surprise
    0.12
     reunited
    0.11
     smugg
    0.11
     reun
    0.11
    visit
    0.11
    Activations Density 0.024%

    No Known Activations