© 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. 30237
    Prev
    Next
    INDEX
    Explanations

    enabling or improving certain aspects

    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
     carefully
    -0.11
     unsuccessfully
    -0.11
     Jah
    -0.10
     inters
    -0.10
     Terr
    -0.10
    aq
    -0.10
     supplemented
    -0.10
     regret
    -0.10
    wy
    -0.10
    odate
    -0.10
    POSITIVE LOGITS
     allowing
    0.14
     helping
    0.13
     helps
    0.13
     thereby
    0.12
     Helps
    0.12
     immensely
    0.12
     tremendously
    0.11
     allows
    0.11
     improves
    0.11
     enabling
    0.11
    Activations Density 0.642%

    No Known Activations