© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16884
    Prev
    Next
    INDEX
    Explanations

    osmolarity, cytoskeleton, thoracotomy

    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
    (and
    -0.13
    aret
    -0.10
    (always
    -0.09
    oho
    -0.09
     PLUS
    -0.09
    (done
    -0.09
    enk
    -0.09
     albeit
    -0.09
    /etc
    -0.09
    (using
    -0.09
    POSITIVE LOGITS
     (=
    0.30
     [=
    0.23
     (
    0.23
    —that
    0.22
     [
    0.21
     (“
    0.19
    —a
    0.18
    —the
    0.17
    *
    0.17
     ie
    0.17
    Activations Density 2.729%

    No Known Activations