© 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. 116925
    Prev
    Next
    INDEX
    Explanations

    way

    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
     Bi
    -0.10
    Uni
    -0.10
    649
    -0.10
     Lambert
    -0.10
    ucci
    -0.10
    vas
    -0.10
    uled
    -0.09
    oki
    -0.09
    IDD
    -0.09
     Aless
    -0.09
    POSITIVE LOGITS
     way
    0.22
     Way
    0.19
    æĸ¹å¼ı
    0.17
     WAY
    0.17
     hard
    0.16
    _way
    0.16
    Way
    0.15
     ways
    0.15
    -way
    0.15
     HARD
    0.14
    Activations Density 0.182%

    No Known Activations