© 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. 8289
    Prev
    Next
    INDEX
    Explanations

    friends and family gatherings

    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
     alongside
    -0.12
     together
    -0.11
     partnering
    -0.11
    partner
    -0.10
     teamed
    -0.10
    (Mod
    -0.10
     enlist
    -0.10
     Burb
    -0.10
    along
    -0.10
     partnered
    -0.10
    POSITIVE LOGITS
     indigenous
    0.09
     preced
    0.09
    uzzi
    0.09
     pot
    0.09
     unrecognized
    0.09
     whom
    0.09
    df
    0.09
    fd
    0.08
     native
    0.08
    Birthday
    0.08
    Activations Density 0.039%

    No Known Activations