© 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. 117603
    Prev
    Next
    INDEX
    Explanations

    how did you do

    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
    ieux
    -0.10
     anx
    -0.09
     PROT
    -0.09
    cer
    -0.09
    RTC
    -0.09
    Ãģ
    -0.09
     overl
    -0.09
     cer
    -0.09
    acher
    -0.08
    odb
    -0.08
    POSITIVE LOGITS
     halfway
    0.09
    eph
    0.09
     Greenwood
    0.08
    itto
    0.08
    issen
    0.08
    inclusive
    0.08
     Leonardo
    0.08
     rep
    0.08
     crossover
    0.08
     Karen
    0.08
    Activations Density 0.020%

    No Known Activations