© 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. 90416
    Prev
    Next
    INDEX
    Explanations

    three or tri combinations

    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
     batches
    -0.11
     downtown
    -0.09
     Classes
    -0.09
     flush
    -0.09
    ighb
    -0.09
     reopening
    -0.08
     litter
    -0.08
    unci
    -0.08
     detention
    -0.08
     drip
    -0.08
    POSITIVE LOGITS
     threesome
    0.19
     third
    0.16
     simultaneous
    0.15
     tri
    0.15
     simult
    0.15
     participant
    0.14
     Tri
    0.14
     bisexual
    0.14
     participation
    0.14
     triplet
    0.13
    Activations Density 0.035%

    No Known Activations