© 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. 46259
    Prev
    Next
    INDEX
    Explanations

    among the

    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
    baum
    -0.09
    658
    -0.09
     Clo
    -0.09
    ataka
    -0.09
    rsa
    -0.09
     Bris
    -0.09
    cbc
    -0.09
    aring
    -0.09
    Clo
    -0.09
    avo
    -0.08
    POSITIVE LOGITS
    /form
    0.10
    xin
    0.09
     disgu
    0.08
     league
    0.08
    -league
    0.08
    Acts
    0.08
    iT
    0.08
     NAMES
    0.08
    hip
    0.08
     names
    0.08
    Activations Density 0.005%

    No Known Activations