© 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. 50982
    Prev
    Next
    INDEX
    Explanations

    related products, reviews, html

    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
    MIC
    -0.09
    OMIC
    -0.09
    anker
    -0.09
     volum
    -0.09
     Harding
    -0.09
     hear
    -0.09
     Silence
    -0.09
    RAL
    -0.09
     cairo
    -0.09
    ail
    -0.08
    POSITIVE LOGITS
    dana
    0.11
     inconsist
    0.10
     Stra
    0.09
    DTD
    0.09
     walker
    0.08
     Consort
    0.08
    foy
    0.08
    sono
    0.08
    .criteria
    0.08
     ignorant
    0.08
    Activations Density 0.001%

    No Known Activations