© 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. 50144
    Prev
    Next
    INDEX
    Explanations

    consideration and forms words ending in 'ations'

    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
     considering
    -0.13
     Considering
    -0.13
    Considering
    -0.12
     considerations
    -0.12
    uding
    -0.12
     considered
    -0.12
     considerable
    -0.11
    lef
    -0.11
     consideration
    -0.11
     Feinstein
    -0.11
    POSITIVE LOGITS
    ate
    0.18
    ately
    0.17
    ations
    0.16
    ation
    0.15
    ably
    0.14
    ATE
    0.12
    aten
    0.11
    ATION
    0.11
    er
    0.11
    azioni
    0.10
    Activations Density 0.054%

    No Known Activations