© 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. 87613
    Prev
    Next
    INDEX
    Explanations

    a lot of / considerable / little / some + discussion or state

    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
    stadt
    -0.08
    strup
    -0.08
    IVA
    -0.08
     successive
    -0.08
    inden
    -0.07
    gard
    -0.07
     Sidebar
    -0.07
     Submission
    -0.07
    omi
    -0.07
     taxing
    -0.07
    POSITIVE LOGITS
     overlap
    0.17
     debate
    0.16
     speculation
    0.14
     stigma
    0.14
     confusion
    0.13
     controversy
    0.13
     rejo
    0.13
     demand
    0.13
     happening
    0.12
    overlap
    0.12
    Activations Density 0.086%

    No Known Activations