© 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. 92316
    Prev
    Next
    INDEX
    Explanations

    source code comments and definitions

    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
    s
    -0.22
    a
    -0.16
    Bid
    -0.14
    d
    -0.14
    Cad
    -0.13
    p
    -0.13
    t
    -0.13
     Grandma
    -0.13
    six
    -0.13
    m
    -0.13
    POSITIVE LOGITS
    AAA
    0.07
    ÑģÑı
    0.06
    PlainText
    0.06
    United
    0.06
    sock
    0.06
    gether
    0.06
    AMPL
    0.06
    ABS
    0.06
    ???
    0.06
    Ó
    0.06
    Activations Density 0.052%

    No Known Activations