© 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. 8114
    Prev
    Next
    INDEX
    Explanations

    broadcast receiver or audience

    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
    kind
    -0.09
    cales
    -0.09
    ¦
    -0.08
    airo
    -0.08
    asco
    -0.08
    ocard
    -0.08
    auer
    -0.08
     Dixon
    -0.08
    reh
    -0.08
     whisk
    -0.08
    POSITIVE LOGITS
    ed
    0.19
    /stream
    0.14
    eer
    0.13
    edBy
    0.13
    ers
    0.13
    edly
    0.12
    edb
    0.12
    ein
    0.11
    eur
    0.11
    igate
    0.11
    Activations Density 0.049%

    No Known Activations