© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16360
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by other words

    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
     enthusi
    -0.11
    inan
    -0.10
     cosy
    -0.10
    SystemService
    -0.10
     bona
    -0.10
    achat
    -0.10
    uta
    -0.10
     gaz
    -0.09
     Coch
    -0.09
     freaking
    -0.09
    POSITIVE LOGITS
     one
    0.10
     verse
    0.10
     group
    0.09
     section
    0.09
     doses
    0.09
     chemotherapy
    0.09
     series
    0.09
     jurors
    0.09
     missed
    0.08
     ones
    0.08
    Activations Density 0.014%

    No Known Activations