© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28199
    Prev
    Next
    INDEX
    Explanations

    Gloria and glory

    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
    bone
    -0.11
    oko
    -0.10
     lại
    -0.10
     pred
    -0.09
    ual
    -0.08
    thal
    -0.08
    sworth
    -0.08
    elog
    -0.08
    ohn
    -0.08
    :focus
    -0.08
    POSITIVE LOGITS
    atory
    0.13
    eve
    0.12
     moot
    0.11
    auc
    0.11
     Vanderbilt
    0.10
    uzzer
    0.10
    cle
    0.10
    -days
    0.10
     minded
    0.10
    onen
    0.09
    Activations Density 0.012%

    No Known Activations