© 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. 31620
    Prev
    Next
    INDEX
    Explanations

    effectively or successfully

    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
     Jam
    -0.12
     dere
    -0.11
     thé
    -0.11
     jam
    -0.10
     ALSO
    -0.10
     reco
    -0.10
    inha
    -0.09
     admittedly
    -0.09
     dep
    -0.09
    ste
    -0.09
    POSITIVE LOGITS
     extensively
    0.18
     effectively
    0.16
     quite
    0.15
     thoroughly
    0.14
     fairly
    0.13
     proficient
    0.12
     efficiently
    0.12
     nicely
    0.12
     prolific
    0.12
     heavily
    0.12
    Activations Density 0.481%

    No Known Activations