© 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. 26165
    Prev
    Next
    INDEX
    Explanations

    in a way / many ways / any 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
    atrice
    -0.11
     reb
    -0.11
    Carthy
    -0.11
    iska
    -0.10
    ateurs
    -0.10
     fellow
    -0.10
     stap
    -0.10
     hastily
    -0.10
    urma
    -0.10
     unanimous
    -0.10
    POSITIVE LOGITS
     ways
    0.40
     way
    0.31
     Ways
    0.29
    æĸ¹å¼ı
    0.24
    ways
    0.23
     Way
    0.20
     manner
    0.20
    way
    0.20
    .way
    0.19
     somew
    0.18
    Activations Density 0.182%

    No Known Activations