© 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. 46153
    Prev
    Next
    INDEX
    Explanations

    New Jersey

    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
    Runner
    -0.11
     pard
    -0.10
    gems
    -0.10
    elper
    -0.10
    Plus
    -0.10
    aris
    -0.10
    Containing
    -0.10
    uite
    -0.10
    unte
    -0.10
    istar
    -0.10
    POSITIVE LOGITS
    ÑĮÑİ
    0.10
     nj
    0.10
     swallowed
    0.08
     shore
    0.08
    bew
    0.08
    SPATH
    0.08
     Herald
    0.08
    lesi
    0.08
     Raum
    0.08
     NJ
    0.08
    Activations Density 0.035%

    No Known Activations