© 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. 14139
    Prev
    Next
    INDEX
    Explanations

    sing and related words

    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
    fat
    -0.10
     illustration
    -0.09
    burger
    -0.09
    oci
    -0.09
     dep
    -0.09
    OCI
    -0.09
     brace
    -0.09
     gim
    -0.09
    -fat
    -0.08
    ISC
    -0.08
    POSITIVE LOGITS
     praises
    0.09
     Sterling
    0.09
     Titan
    0.09
     Prescott
    0.09
    Claims
    0.09
     batch
    0.09
     Herman
    0.09
     Vit
    0.08
     songs
    0.08
     Livingston
    0.08
    Activations Density 0.002%

    No Known Activations