© 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. 50881
    Prev
    Next
    INDEX
    Explanations

    full + [noun]

    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
     Narrow
    -0.09
     Duffy
    -0.08
    cest
    -0.08
    .aw
    -0.08
     entirety
    -0.08
    lots
    -0.08
    å£
    -0.08
     POSSIBILITY
    -0.08
    akt
    -0.08
     narrow
    -0.08
    POSITIVE LOGITS
     blown
    0.15
     fled
    0.14
     slate
    0.13
     redesign
    0.13
    -bl
    0.13
     suite
    0.13
     functioning
    0.12
     grown
    0.12
    elson
    0.11
    ledged
    0.11
    Activations Density 0.044%

    No Known Activations