© 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. 34240
    Prev
    Next
    INDEX
    Explanations

    .m or News or Variety or number

    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
    efa
    -0.10
     bod
    -0.10
     versus
    -0.09
    (Photo
    -0.09
     decad
    -0.09
    ofil
    -0.08
     disg
    -0.08
     tranquil
    -0.08
     thrott
    -0.08
     peach
    -0.08
    POSITIVE LOGITS
     Salon
    0.16
    asso
    0.10
     Mic
    0.10
     Ibn
    0.10
     Kitt
    0.10
     Tunis
    0.09
     Nev
    0.09
     Rede
    0.09
    hw
    0.09
    Mic
    0.09
    Activations Density 0.111%

    No Known Activations