© 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. 92163
    Prev
    Next
    INDEX
    Explanations

    oldest or older comparisons

    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
    prev
    -0.11
     past
    -0.11
    Prev
    -0.11
    308
    -0.10
     Camden
    -0.10
     Past
    -0.10
    Past
    -0.10
    Previous
    -0.10
    Ìģ
    -0.09
     Prev
    -0.09
    POSITIVE LOGITS
     oldest
    0.42
     older
    0.29
     Older
    0.23
    older
    0.23
     vener
    0.22
     age
    0.21
     vieux
    0.20
     eldest
    0.20
     aged
    0.19
     longevity
    0.19
    Activations Density 0.328%

    No Known Activations