© 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. 46017
    Prev
    Next
    INDEX
    Explanations

    trying to do something

    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
    arf
    -0.11
    greg
    -0.10
     underside
    -0.10
     coherent
    -0.10
    ifo
    -0.10
    uzz
    -0.10
     magn
    -0.09
     surre
    -0.09
     honoring
    -0.08
    avin
    -0.08
    POSITIVE LOGITS
     different
    0.14
     new
    0.13
     harder
    0.12
    different
    0.11
     trial
    0.11
     strategies
    0.11
    new
    0.10
     Different
    0.10
    æĸ°
    0.10
     newer
    0.10
    Activations Density 0.054%

    No Known Activations