© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50773
    Prev
    Next
    INDEX
    Explanations

    altogether or completely

    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
    Negative Logits
    erk
    -0.11
    Kir
    -0.10
    934
    -0.10
    inus
    -0.10
    kir
    -0.10
    je
    -0.10
     Kirby
    -0.10
    crest
    -0.09
     Klo
    -0.09
     Unauthorized
    -0.09
    POSITIVE LOGITS
     altogether
    1.01
     entirely
    0.71
    alto
    0.60
     completely
    0.54
     Alto
    0.51
     Completely
    0.41
     outright
    0.41
     totally
    0.41
     alto
    0.38
     wholly
    0.38
    Activations Density 0.583%

    No Known Activations