© 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. 50646
    Prev
    Next
    INDEX
    Explanations

    perform actions or feats

    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
    entic
    -0.13
    _perf
    -0.12
    rates
    -0.12
    worth
    -0.11
    elper
    -0.11
     provision
    -0.11
     Faul
    -0.11
    .embed
    -0.11
    opher
    -0.10
    form
    -0.10
    POSITIVE LOGITS
     miracles
    0.13
    ative
    0.12
    ances
    0.11
     arts
    0.11
    ace
    0.11
    Segue
    0.10
    atted
    0.10
     CPR
    0.10
     trou
    0.10
     feats
    0.09
    Activations Density 0.087%

    No Known Activations