© 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. 31116
    Prev
    Next
    INDEX
    Explanations

    modern -day

    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
     later
    -0.10
     Victorian
    -0.09
    olds
    -0.09
    anc
    -0.08
     Laud
    -0.08
     prematurely
    -0.07
    yla
    -0.07
     ambit
    -0.07
     Biblical
    -0.07
     ancient
    -0.07
    POSITIVE LOGITS
    -day
    0.26
    -Day
    0.20
    day
    0.17
    -era
    0.15
     day
    0.15
    aday
    0.14
    /post
    0.12
    /day
    0.11
     equivalents
    0.11
     times
    0.11
    Activations Density 0.284%

    No Known Activations