© 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. 18733
    Prev
    Next
    INDEX
    Explanations

    recommendations / recommended citations

    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
    spa
    -0.11
    iously
    -0.09
    perm
    -0.09
     rend
    -0.08
    gas
    -0.08
     Silva
    -0.08
    pin
    -0.08
    cu
    -0.08
    pac
    -0.08
    isans
    -0.08
    POSITIVE LOGITS
    adt
    0.14
    ations
    0.13
    ATIONS
    0.11
    haar
    0.11
    atory
    0.11
     strongly
    0.10
    erer
    0.10
    аÑĤелÑĮ
    0.10
    ENC
    0.10
    ation
    0.10
    Activations Density 0.043%

    No Known Activations