© 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. 5604
    Prev
    Next
    INDEX
    Explanations

    health and social characteristics

    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
     dissoci
    -0.09
     amongst
    -0.08
    Normally
    -0.08
     Waterloo
    -0.08
     stom
    -0.08
    steel
    -0.08
     paed
    -0.08
    borg
    -0.08
    ÑĪе
    -0.08
     Basel
    -0.08
    POSITIVE LOGITS
     Pew
    0.17
     respondent
    0.13
     Gallup
    0.13
     respondents
    0.13
     household
    0.13
     households
    0.13
     Census
    0.12
     substantive
    0.12
     Household
    0.12
     Interracial
    0.11
    Activations Density 1.248%

    No Known Activations