© 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. 92517
    Prev
    Next
    INDEX
    Explanations

    is [state/characteristic]

    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
     Klo
    -0.11
    hill
    -0.10
     postponed
    -0.10
    .same
    -0.08
     Meer
    -0.08
     busted
    -0.08
     Blackburn
    -0.08
    ableView
    -0.08
     forgiven
    -0.08
    aur
    -0.08
    POSITIVE LOGITS
     accompanied
    0.12
     nomin
    0.11
     actually
    0.11
     subdiv
    0.11
     unusual
    0.11
     responsible
    0.10
     courtesy
    0.10
    actually
    0.10
     located
    0.10
     followed
    0.10
    Activations Density 0.409%

    No Known Activations