© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 28921
    Prev
    Next
    INDEX
    Explanations

    family, couple, marriage

    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
     Cyril
    -0.12
     Scotia
    -0.10
     mon
    -0.10
     Prairie
    -0.10
     Westminster
    -0.10
     mec
    -0.10
     coc
    -0.10
    Tac
    -0.10
     Mixed
    -0.10
     Marina
    -0.09
    POSITIVE LOGITS
     family
    0.19
    family
    0.13
     Clintons
    0.13
     Whites
    0.13
    -family
    0.13
     Blacks
    0.13
     elder
    0.12
     Johnson
    0.12
     Smith
    0.12
     couple
    0.12
    Activations Density 0.281%

    No Known Activations