© 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. 111700
    Prev
    Next
    INDEX
    Explanations

    more than

    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
     slightly
    -0.13
     exactly
    -0.13
    ully
    -0.11
    ipa
    -0.11
    umen
    -0.11
    rego
    -0.11
     Evo
    -0.10
     somewhat
    -0.10
    actly
    -0.10
     Exactly
    -0.10
    POSITIVE LOGITS
     than
    0.16
    than
    0.14
    inds
    0.12
    Than
    0.11
     Than
    0.10
     fiance
    0.10
     stranger
    0.09
     Spicer
    0.09
    inde
    0.08
     fian
    0.08
    Activations Density 0.091%

    No Known Activations