© 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. 91427
    Prev
    Next
    INDEX
    Explanations

    License, warranty, disclaimer

    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
    isos
    -0.09
     Cory
    -0.09
     cries
    -0.09
     vo
    -0.09
     Rut
    -0.08
    ede
    -0.08
     comm
    -0.08
    Licensed
    -0.08
    endon
    -0.08
    mat
    -0.08
    POSITIVE LOGITS
    usher
    0.12
    arness
    0.09
     canon
    0.09
     continuation
    0.09
    borg
    0.08
    anine
    0.08
     Mand
    0.08
     Disclaimer
    0.08
     copp
    0.08
     barr
    0.08
    Activations Density 0.001%

    No Known Activations