© 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. 26558
    Prev
    Next
    INDEX
    Explanations

    archives, news, and publications

    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
     annual
    -0.10
     sle
    -0.08
     Joh
    -0.08
    mi
    -0.08
    ibo
    -0.08
     Wol
    -0.08
    /O
    -0.08
     dates
    -0.08
     Annual
    -0.08
     magn
    -0.08
    POSITIVE LOGITS
     GK
    0.11
    /API
    0.11
     inspiration
    0.11
     cams
    0.11
     Inspiration
    0.11
     wd
    0.11
     conte
    0.10
     inspir
    0.10
     GRAT
    0.10
    egg
    0.10
    Activations Density 0.007%

    No Known Activations