© 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. 15289
    Prev
    Next
    INDEX
    Explanations

    speed or performance

    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
     osg
    -0.10
    nop
    -0.10
    ONO
    -0.09
    deaux
    -0.09
    ¬¸
    -0.09
     creatively
    -0.09
    åľŁ
    -0.09
    gis
    -0.09
     scri
    -0.09
     Sass
    -0.09
    POSITIVE LOGITS
     speed
    0.72
     speeds
    0.66
     Speed
    0.62
     faster
    0.60
     speeding
    0.60
    Speed
    0.59
     slower
    0.59
    -speed
    0.59
    speed
    0.58
    éĢŁ
    0.57
    Activations Density 1.106%

    No Known Activations