© 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. 32226
    Prev
    Next
    INDEX
    Explanations

    common English word endings /i/ /en/ /er/ /is/ /at/

    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
     afterwards
    -0.10
     Concat
    -0.10
    Concat
    -0.09
    avin
    -0.09
     affirmative
    -0.09
     Anatomy
    -0.09
    esteem
    -0.09
     desp
    -0.09
    .addAll
    -0.09
    .toUpperCase
    -0.09
    POSITIVE LOGITS
    anas
    0.11
     Wass
    0.09
     Till
    0.09
    ظ
    0.09
    alist
    0.09
     Thy
    0.09
     silenced
    0.08
    oder
    0.08
    æ¼
    0.08
    plant
    0.08
    Activations Density 0.002%

    No Known Activations