© 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. 3638
    Prev
    Next
    INDEX
    Explanations

    stage performances

    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
     neighbour
    -0.13
     conversations
    -0.11
     neighbor
    -0.11
     dossier
    -0.10
     companions
    -0.10
     conversation
    -0.10
     companion
    -0.10
     impatient
    -0.10
    conversation
    -0.10
     Convers
    -0.10
    POSITIVE LOGITS
     audience
    0.34
     onstage
    0.34
     Audience
    0.29
     audiences
    0.28
     crowd
    0.22
     stage
    0.22
     performers
    0.21
     applause
    0.20
     backstage
    0.20
     Crowd
    0.19
    Activations Density 0.020%

    No Known Activations