© 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. 92477
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    ervo
    -0.10
    mmo
    -0.10
    amel
    -0.10
     ordin
    -0.10
     uy
    -0.10
    zion
    -0.10
    byss
    -0.09
     cre
    -0.09
     polic
    -0.09
    itoris
    -0.09
    POSITIVE LOGITS
     afterwards
    0.17
     afterward
    0.16
     Afterwards
    0.15
     post
    0.15
    (before
    0.13
    -before
    0.13
     before
    0.13
     aft
    0.13
    /post
    0.12
     Before
    0.12
    Activations Density 0.194%

    No Known Activations