© 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. 8042
    Prev
    Next
    INDEX
    Explanations

    multiple entities together

    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
     duo
    -0.17
    两
    -0.14
     two
    -0.14
    two
    -0.13
     pair
    -0.13
     twin
    -0.12
     respective
    -0.12
    Two
    -0.11
     zwei
    -0.11
     respectively
    -0.11
    POSITIVE LOGITS
     together
    0.16
     altogether
    0.14
     gathered
    0.13
     piled
    0.12
     interconnected
    0.12
     clustered
    0.12
     pile
    0.12
     Together
    0.12
     gatherings
    0.11
     tangled
    0.11
    Activations Density 0.170%

    No Known Activations