© 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. 8196
    Prev
    Next
    INDEX
    Explanations

    X-to-Y connections

    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
     alike
    -0.11
    stars
    -0.10
    à¹Į
    -0.10
    ,—
    -0.10
     neither
    -0.10
    ands
    -0.10
    /pro
    -0.10
    ifu
    -0.10
    ó
    -0.09
     both
    -0.09
    POSITIVE LOGITS
    ilon
    0.08
    resco
    0.08
     Doll
    0.08
     bre
    0.08
     Blasio
    0.08
     Met
    0.07
     Lima
    0.07
     zab
    0.07
     Dunn
    0.07
     Pip
    0.07
    Activations Density 0.024%

    No Known Activations