© 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. 30656
    Prev
    Next
    INDEX
    Explanations

    human connection and interaction

    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
     Flip
    -0.11
     obedient
    -0.09
    scribe
    -0.09
     ingr
    -0.09
     preparations
    -0.09
     bride
    -0.09
     jealous
    -0.09
     summons
    -0.09
     suspense
    -0.09
     scr
    -0.09
    POSITIVE LOGITS
     connection
    0.19
     human
    0.16
     shared
    0.16
     connect
    0.16
     connections
    0.16
     Connection
    0.15
     touch
    0.15
     communion
    0.15
     connecting
    0.15
     companions
    0.14
    Activations Density 0.025%

    No Known Activations