© 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. 50455
    Prev
    Next
    INDEX
    Explanations

    once in a lifetime, awhile, twice

    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
    nit
    -0.10
    rust
    -0.10
    ddb
    -0.09
     desk
    -0.09
    agnost
    -0.09
    yu
    -0.09
     Byron
    -0.09
     plank
    -0.09
    unte
    -0.09
    iage
    -0.09
    POSITIVE LOGITS
     Twice
    0.17
     twice
    0.16
     einmal
    0.11
    itten
    0.10
     lifetime
    0.09
     briefly
    0.09
     Lifetime
    0.09
    -tw
    0.09
     awhile
    0.09
     Lac
    0.09
    Activations Density 0.063%

    No Known Activations