© 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. 6134
    Prev
    Next
    INDEX
    Explanations

    assumptions and resolutions

    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
    Depending
    -0.11
     Depending
    -0.11
     hopefully
    -0.10
     gib
    -0.10
     depending
    -0.10
     Logical
    -0.10
     thankfully
    -0.10
     selective
    -0.10
     proper
    -0.10
     Sammy
    -0.10
    POSITIVE LOGITS
     err
    0.29
     assume
    0.28
     presumption
    0.27
     errs
    0.25
     assumption
    0.25
     Assume
    0.25
     Err
    0.25
     assumed
    0.25
    assume
    0.24
     presume
    0.24
    Activations Density 0.267%

    No Known Activations