© 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. 91692
    Prev
    Next
    INDEX
    Explanations

    radiat

    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
    eling
    -0.09
    ably
    -0.08
    tings
    -0.08
    mods
    -0.08
     Garrett
    -0.08
    houses
    -0.08
    smart
    -0.07
    sw
    -0.07
    ifications
    -0.07
    spaces
    -0.07
    POSITIVE LOGITS
    opacity
    0.13
    activo
    0.13
     radiation
    0.12
     radi
    0.12
    opaque
    0.12
    /opt
    0.12
     eman
    0.12
    .Rad
    0.11
     emission
    0.11
    onde
    0.11
    Activations Density 0.264%

    No Known Activations