© 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. 18513
    Prev
    Next
    INDEX
    Explanations

    William or Willie, followed by names

    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
    s
    -0.13
    edin
    -0.08
    esy
    -0.08
    ed
    -0.07
    nos
    -0.07
     Pact
    -0.07
    orney
    -0.07
     retro
    -0.07
     fret
    -0.07
    IDE
    -0.06
    POSITIVE LOGITS
    kommen
    0.20
    aims
    0.17
    ough
    0.16
    cox
    0.15
    ard
    0.15
    iam
    0.15
    imas
    0.15
    owy
    0.14
    helm
    0.14
    ikers
    0.14
    Activations Density 0.043%

    No Known Activations