© 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. 92310
    Prev
    Next
    INDEX
    Explanations

    conditions that manifest or arise

    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
     MADE
    -0.11
     flirt
    -0.11
     ach
    -0.11
     hic
    -0.11
     Ach
    -0.11
     grands
    -0.10
    Ping
    -0.10
    phis
    -0.10
    985
    -0.10
     sucked
    -0.10
    POSITIVE LOGITS
     arises
    0.15
     arise
    0.14
     stems
    0.14
     manifest
    0.14
     persisted
    0.13
     persists
    0.12
     manifests
    0.12
    manifest
    0.12
     Manifest
    0.12
     persistence
    0.12
    Activations Density 0.644%

    No Known Activations