© 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. 17792
    Prev
    Next
    INDEX
    Explanations

    conditional "would"

    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
     will
    -0.13
     sometimes
    -0.13
    will
    -0.13
     WILL
    -0.12
     Sometimes
    -0.12
    can
    -0.12
    Sometimes
    -0.12
     can
    -0.11
    sometimes
    -0.11
     often
    -0.10
    POSITIVE LOGITS
     would
    0.43
     Would
    0.42
    would
    0.41
    Would
    0.38
     wouldn
    0.34
     Wouldn
    0.28
     serait
    0.27
     würde
    0.24
     wäre
    0.21
     could
    0.21
    Activations Density 0.650%

    No Known Activations