© 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. 14164
    Prev
    Next
    INDEX
    Explanations

    section citation markers

    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
    .NET
    -0.10
    emble
    -0.10
     Kauf
    -0.09
    adc
    -0.09
     Equip
    -0.09
     Hof
    -0.09
    chu
    -0.09
    olib
    -0.09
    imagin
    -0.08
     Huck
    -0.08
    POSITIVE LOGITS
    fully
    0.10
    è¡
    0.09
    ically
    0.09
    ingly
    0.09
    wise
    0.09
    arily
    0.09
     flush
    0.09
    ally
    0.09
     Blair
    0.09
    raf
    0.09
    Activations Density 0.017%

    No Known Activations