© 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. 3469
    Prev
    Next
    INDEX
    Explanations

    thrombus or thrombin

    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
    anya
    -0.08
    oter
    -0.08
    iard
    -0.08
    d
    -0.08
    elijke
    -0.08
    ará
    -0.08
     clumsy
    -0.08
    eny
    -0.08
    544
    -0.08
     delegated
    -0.08
    POSITIVE LOGITS
     thro
    0.14
    bbing
    0.14
    bose
    0.13
    bus
    0.11
     thrust
    0.10
     throws
    0.10
     Thr
    0.10
    /con
    0.10
     Thorn
    0.10
     tro
    0.10
    Activations Density 0.004%

    No Known Activations