© 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. 111738
    Prev
    Next
    INDEX
    Explanations

    action, behavior, thought, measurement, writing

    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
    iras
    -0.11
     Sadd
    -0.11
    aub
    -0.11
     Mitch
    -0.10
    irl
    -0.10
    UGH
    -0.10
     contro
    -0.10
    zej
    -0.10
    etxt
    -0.10
    /Dk
    -0.10
    POSITIVE LOGITS
    echa
    0.09
     Kok
    0.08
     Affairs
    0.08
    ishing
    0.07
     Juda
    0.07
    thern
    0.07
     nowhere
    0.07
     Excellence
    0.07
     bisc
    0.07
     fused
    0.07
    Activations Density 0.698%

    No Known Activations