© 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. 30438
    Prev
    Next
    INDEX
    Explanations

    earalenone contamination

    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
    imap
    -0.12
     Moder
    -0.10
    iro
    -0.10
    imas
    -0.10
    assi
    -0.10
     Prim
    -0.10
    uther
    -0.10
     loose
    -0.10
    thead
    -0.10
    arp
    -0.10
    POSITIVE LOGITS
     schedules
    0.09
     afterwards
    0.09
    uju
    0.08
     Schedule
    0.08
    nv
    0.08
     schedule
    0.08
     Afterwards
    0.08
    vik
    0.07
     silent
    0.07
     fet
    0.07
    Activations Density 0.001%

    No Known Activations