© 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. 111533
    Prev
    Next
    INDEX
    Explanations

    type, duration, location, KIND

    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
    Fight
    -0.08
     fights
    -0.08
     Tomorrow
    -0.07
     surgeries
    -0.07
    zl
    -0.07
     Ley
    -0.07
     Heights
    -0.07
     Capability
    -0.07
    iele
    -0.07
     discussions
    -0.07
    POSITIVE LOGITS
     type
    0.17
     location
    0.16
     perman
    0.15
     duration
    0.15
     mode
    0.14
     locale
    0.14
    type
    0.13
     KIND
    0.13
     kind
    0.13
     geographical
    0.12
    Activations Density 0.649%

    No Known Activations