© 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. 89144
    Prev
    Next
    INDEX
    Explanations

    couple introducing others

    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
     jointly
    -0.17
     co
    -0.13
     couples
    -0.13
     joint
    -0.12
    Together
    -0.11
     together
    -0.11
     pairs
    -0.11
     Together
    -0.11
     Couples
    -0.11
     Regions
    -0.11
    POSITIVE LOGITS
     hail
    0.10
     met
    0.09
     defe
    0.09
     newcomers
    0.08
     another
    0.08
    gings
    0.08
    Statics
    0.08
     Guest
    0.08
     repl
    0.08
     nack
    0.08
    Activations Density 0.149%

    No Known Activations