© 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. 17526
    Prev
    Next
    INDEX
    Explanations

    take to the next level

    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
     Dro
    -0.12
     cre
    -0.11
     Bryan
    -0.10
    ookie
    -0.10
     taken
    -0.10
    iese
    -0.10
    çº
    -0.10
     repl
    -0.10
    tractor
    -0.09
     Creed
    -0.09
    POSITIVE LOGITS
     nowhere
    0.15
     seriously
    0.13
     back
    0.12
     hostage
    0.12
     Seriously
    0.11
     closer
    0.10
    uring
    0.10
     indoors
    0.10
     forward
    0.10
     apart
    0.10
    Activations Density 0.088%

    No Known Activations