© 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. 18592
    Prev
    Next
    INDEX
    Explanations

    let's plus verb

    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
    zu
    -0.11
     Dop
    -0.11
    uat
    -0.10
    rey
    -0.10
    PLUS
    -0.10
     forg
    -0.10
     pardon
    -0.10
     Goodman
    -0.10
     resist
    -0.10
     Forg
    -0.10
    POSITIVE LOGITS
     together
    0.20
     ourselves
    0.15
     Together
    0.13
    Together
    0.11
    gether
    0.09
     mutually
    0.09
     jointly
    0.09
    !↵↵
    0.08
     sometime
    0.08
     discuss
    0.08
    Activations Density 0.089%

    No Known Activations