© 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. 114405
    Prev
    Next
    INDEX
    Explanations

    seeking partners or collaborators

    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
     jus
    -0.08
    rica
    -0.08
     unconscious
    -0.08
     approaching
    -0.07
     demand
    -0.07
     registr
    -0.07
     choices
    -0.07
     registrar
    -0.07
     repell
    -0.07
     selection
    -0.07
    POSITIVE LOGITS
     partners
    0.17
     companions
    0.16
     partner
    0.15
    partner
    0.14
     partnership
    0.14
     friendship
    0.14
     collaborators
    0.13
     companion
    0.13
     teammates
    0.13
    wart
    0.12
    Activations Density 0.008%

    No Known Activations