© 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. 4552
    Prev
    Next
    INDEX
    Explanations

    life, family, professional lives

    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
    adt
    -0.08
    rend
    -0.08
     Dalton
    -0.08
    cks
    -0.08
    alen
    -0.07
    f
    -0.07
    edom
    -0.07
    isman
    -0.07
     Garn
    -0.07
     their
    -0.07
    POSITIVE LOGITS
     antics
    0.21
     lives
    0.19
     plight
    0.18
     workings
    0.17
     whereabouts
    0.17
     ambitions
    0.17
     fortunes
    0.17
     aspirations
    0.16
     interests
    0.16
     talents
    0.16
    Activations Density 1.914%

    No Known Activations