© 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. 117590
    Prev
    Next
    INDEX
    Explanations

    twin relationships and compounds

    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
    yle
    -0.09
    uggy
    -0.09
     others
    -0.09
     Others
    -0.09
     turn
    -0.09
     enlightened
    -0.08
     partner
    -0.08
     Turn
    -0.08
    ilen
    -0.08
    Others
    -0.08
    POSITIVE LOGITS
     Peaks
    0.14
     peaks
    0.14
     Rivers
    0.13
     Ronnie
    0.11
     evils
    0.10
     annoy
    0.10
     rivers
    0.10
     centroids
    0.10
    zin
    0.10
    eton
    0.10
    Activations Density 0.008%

    No Known Activations