© 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. 46317
    Prev
    Next
    INDEX
    Explanations

    become, arrive, appear

    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
     wurden
    -0.09
     showed
    -0.09
    )did
    -0.09
    _are
    -0.09
     DON
    -0.08
    Are
    -0.08
    don
    -0.08
     sont
    -0.08
     Are
    -0.08
     sang
    -0.08
    POSITIVE LOGITS
     emerge
    0.27
     become
    0.27
     arrive
    0.25
     disappear
    0.25
     come
    0.25
     evolve
    0.24
     begin
    0.22
     arise
    0.21
     appear
    0.20
     take
    0.20
    Activations Density 0.244%

    No Known Activations