© 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. 25261
    Prev
    Next
    INDEX
    Explanations

    add to

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fores
    -0.11
    IW
    -0.09
     Stevens
    -0.09
    rosso
    -0.09
     Poz
    -0.09
     Entire
    -0.09
    741
    -0.08
     forth
    -0.08
    enos
    -0.08
    ugi
    -0.08
    POSITIVE LOGITS
     already
    0.24
    already
    0.20
     existing
    0.20
    existing
    0.19
     Already
    0.18
     repertoire
    0.18
     growing
    0.17
     woes
    0.17
     pile
    0.16
     fray
    0.16
    Activations Density 0.149%

    No Known Activations