© 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. 13976
    Prev
    Next
    INDEX
    Explanations

    States ... 18

    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
     redund
    -0.09
    ↵
    -0.09
     conven
    -0.07
     ilk
    -0.07
     envi
    -0.07
    eeee
    -0.07
     complet
    -0.07
    ãģĸ
    -0.07
     helicopt
    -0.07
    hel
    -0.07
    POSITIVE LOGITS
     $?
    0.11
     tarn
    0.11
    ocol
    0.10
    uish
    0.10
     criticised
    0.10
    ait
    0.10
    isy
    0.10
    Anal
    0.10
     conservative
    0.10
    )?.
    0.10
    Activations Density 0.001%

    No Known Activations