© 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. 32448
    Prev
    Next
    INDEX
    Explanations

    version options

    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
     surprises
    -0.09
    ena
    -0.09
     impress
    -0.09
    allen
    -0.08
     SD
    -0.08
     SF
    -0.08
    rek
    -0.08
     Nagar
    -0.08
    sf
    -0.08
     mode
    -0.08
    POSITIVE LOGITS
     embarked
    0.10
     whatsoever
    0.10
     Oper
    0.10
    implicit
    0.10
     implicit
    0.10
     Imper
    0.10
    /reference
    0.09
     GRAT
    0.09
     Segment
    0.09
     obed
    0.09
    Activations Density 0.007%

    No Known Activations