© 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. 24953
    Prev
    Next
    INDEX
    Explanations

    project_master | end | layer | Lyon | Greenland | space

    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
    698
    -0.10
    rss
    -0.10
    893
    -0.10
    eken
    -0.10
     distr
    -0.10
     kra
    -0.09
    bright
    -0.09
    .jd
    -0.09
    ance
    -0.09
    arse
    -0.09
    POSITIVE LOGITS
     armed
    0.12
     intent
    0.11
     wielding
    0.11
     Nug
    0.10
     Lewis
    0.10
     clo
    0.10
     Clo
    0.10
     positioning
    0.09
     inher
    0.09
     hover
    0.09
    Activations Density 0.019%

    No Known Activations