© 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. 90872
    Prev
    Next
    INDEX
    Explanations

    he is/was

    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
    ued
    -0.09
     sens
    -0.09
     Lump
    -0.09
     Consulting
    -0.09
     consulting
    -0.09
     inde
    -0.09
     reinforce
    -0.08
     Discipline
    -0.08
    fect
    -0.08
     nowadays
    -0.08
    POSITIVE LOGITS
     commute
    0.17
     commuting
    0.16
     earning
    0.11
     responsibilities
    0.11
     earn
    0.11
     duties
    0.10
     earns
    0.10
     miserable
    0.10
     Responsibilities
    0.10
     weekends
    0.10
    Activations Density 0.318%

    No Known Activations