© 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. 87956
    Prev
    Next
    INDEX
    Explanations

    Kam followed by names or places

    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
     Kul
    -0.10
    exus
    -0.10
    uchi
    -0.09
     relief
    -0.09
     mechan
    -0.09
     helpless
    -0.09
     kul
    -0.09
     Rever
    -0.09
     anywhere
    -0.09
     undes
    -0.09
    POSITIVE LOGITS
    loops
    0.12
    uela
    0.11
    bove
    0.10
    ming
    0.10
    ijo
    0.10
    ocha
    0.10
    pha
    0.09
    ienie
    0.09
    .si
    0.09
    inski
    0.09
    Activations Density 0.002%

    No Known Activations