© 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. 92444
    Prev
    Next
    INDEX
    Explanations

    is a

    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
    Negative Logits
     yourselves
    -0.10
    rek
    -0.10
    ith
    -0.10
    olas
    -0.10
    arem
    -0.09
    avs
    -0.09
    zers
    -0.09
     themselves
    -0.09
    asco
    -0.09
     ourselves
    -0.08
    POSITIVE LOGITS
    oris
    0.10
    kur
    0.10
    USR
    0.10
     suffice
    0.10
    /is
    0.10
     ALWAYS
    0.10
    ,a
    0.10
    /a
    0.09
     typically
    0.09
    byn
    0.09
    Activations Density 0.439%

    No Known Activations