© 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. 3663
    Prev
    Next
    INDEX
    Explanations

    hang out

    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
    Not in Any Lists

    No Comments

    Negative Logits
    oller
    -0.11
    leted
    -0.11
     outr
    -0.11
    essler
    -0.11
    byte
    -0.10
    760
    -0.10
     Marathon
    -0.10
     vein
    -0.10
    iske
    -0.10
    uest
    -0.10
    POSITIVE LOGITS
    /work
    0.11
     buddies
    0.09
     chill
    0.09
     drinking
    0.09
     with
    0.09
     backstage
    0.09
     downtown
    0.08
    iale
    0.08
     together
    0.08
     outside
    0.08
    Activations Density 0.008%

    No Known Activations