© 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. 16896
    Prev
    Next
    INDEX
    Explanations

    Paul followed by a name

    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
    /rec
    -0.11
    itzer
    -0.11
    oui
    -0.11
     darm
    -0.11
    alf
    -0.10
     laure
    -0.10
    ias
    -0.10
     Vintage
    -0.10
     Alfred
    -0.10
     Ramsey
    -0.10
    POSITIVE LOGITS
     ada
    0.09
     sponge
    0.09
     dispar
    0.09
    herit
    0.08
    reed
    0.08
     Aware
    0.08
     screened
    0.08
     rep
    0.08
     Associ
    0.08
     Cleanup
    0.08
    Activations Density 0.006%

    No Known Activations