© 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. 117320
    Prev
    Next
    INDEX
    Explanations

    make it

    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
    pires
    -0.10
     Fen
    -0.09
    oco
    -0.09
    icha
    -0.09
    831
    -0.09
     borrow
    -0.09
    stick
    -0.09
     McInt
    -0.09
     Stamp
    -0.09
     Establishment
    -0.09
    POSITIVE LOGITS
     deadline
    0.21
     deadlines
    0.20
     quota
    0.13
    deadline
    0.13
     Deadline
    0.13
     cutoff
    0.12
     quotas
    0.12
     cut
    0.11
     halftime
    0.11
    weight
    0.11
    Activations Density 0.039%

    No Known Activations