© 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. 25076
    Prev
    Next
    INDEX
    Explanations

    Wright's or Wright Brothers

    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
    ajar
    -0.10
    ****/↵
    -0.10
     Nail
    -0.10
    *****/↵
    -0.09
    ****
    -0.08
    âĸĪâĸĪ
    -0.08
    icamente
    -0.08
    ear
    -0.08
    orial
    -0.08
    inter
    -0.08
    POSITIVE LOGITS
    ed
    0.12
    âķĹ
    0.11
    edia
    0.10
    sonian
    0.10
    .Sprintf
    0.10
    er
    0.10
    son
    0.09
    erator
    0.09
    âĶĢâĶĢ
    0.09
    ilden
    0.09
    Activations Density 0.117%

    No Known Activations