© 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. 8275
    Prev
    Next
    INDEX
    Explanations

    not ... for, from, in, INSERT

    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
    uhe
    -0.11
    abr
    -0.11
     Chim
    -0.11
    upe
    -0.10
    ioni
    -0.10
    uite
    -0.10
    reste
    -0.10
    ihan
    -0.10
    atta
    -0.10
    zek
    -0.10
    POSITIVE LOGITS
    äºİ
    0.16
     toward
    0.14
     of
    0.13
     for
    0.11
     towards
    0.11
     to
    0.11
     into
    0.11
     against
    0.10
     from
    0.09
    igu
    0.09
    Activations Density 1.054%

    No Known Activations