© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    posted on

    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
    map
    -0.09
    apps
    -0.08
     trait
    -0.08
    omap
    -0.08
    uzz
    -0.08
    ees
    -0.08
    azer
    -0.08
     recurrent
    -0.08
    ede
    -0.07
    ews
    -0.07
    POSITIVE LOGITS
    orsch
    0.10
    ertas
    0.10
    orsche
    0.10
     Speakers
    0.10
    rowable
    0.10
    orney
    0.09
    ublic
    0.09
    BUM
    0.09
     <![
    0.09
    ervice
    0.09
    Activations Density 0.003%

    No Known Activations