© 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. 3355
    Prev
    Next
    INDEX
    Explanations

    sign up phrases

    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
    atte
    -0.11
    ora
    -0.11
    amas
    -0.10
     thanking
    -0.10
     LP
    -0.10
    LY
    -0.10
     flaw
    -0.10
    amos
    -0.10
     biome
    -0.10
    lag
    -0.10
    POSITIVE LOGITS
     newsletters
    0.15
     membership
    0.13
     newsletter
    0.12
     alerts
    0.11
     classes
    0.11
     courses
    0.10
     services
    0.10
     free
    0.10
     memberships
    0.10
    classes
    0.09
    Activations Density 0.064%

    No Known Activations