© 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. 111732
    Prev
    Next
    INDEX
    Explanations

    month names and dates

    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
     moments
    -0.09
    ating
    -0.08
     Bubble
    -0.08
     Thor
    -0.08
    izable
    -0.07
    zelf
    -0.07
    Ĺı
    -0.07
    ITE
    -0.07
     Gol
    -0.07
    riet
    -0.07
    POSITIVE LOGITS
    份
    0.24
    /year
    0.19
    -long
    0.18
    lies
    0.17
    -old
    0.17
    OfYear
    0.15
    iversary
    0.14
    sWith
    0.14
    long
    0.14
     ago
    0.13
    Activations Density 0.075%

    No Known Activations