© 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. 48518
    Prev
    Next
    INDEX
    Explanations

    hunger, poverty, homelessness

    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
     retire
    -0.13
     vacation
    -0.12
     retirement
    -0.11
     vacations
    -0.11
     naughty
    -0.11
     retiring
    -0.10
     tame
    -0.10
     divorced
    -0.10
     competitive
    -0.10
     marry
    -0.10
    POSITIVE LOGITS
     homeless
    0.23
     homelessness
    0.20
     scav
    0.19
     prostitution
    0.17
     poverty
    0.17
     Poverty
    0.17
     shelters
    0.17
     hunger
    0.16
     prostitute
    0.16
     street
    0.15
    Activations Density 0.037%

    No Known Activations