© 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. 116135
    Prev
    Next
    INDEX
    Explanations

    whole-body radiation or brain irradiation

    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
    -more
    -0.10
     gubern
    -0.10
     feather
    -0.10
     enlarged
    -0.10
     dign
    -0.09
     conce
    -0.09
     Bun
    -0.09
    mia
    -0.09
    duk
    -0.09
     CITY
    -0.09
    POSITIVE LOGITS
     including
    0.10
    /system
    0.10
     involvement
    0.10
     shortcuts
    0.09
     Ry
    0.09
     scans
    0.09
    /world
    0.09
    Including
    0.09
     experience
    0.08
     Including
    0.08
    Activations Density 0.046%

    No Known Activations