© 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. 30190
    Prev
    Next
    INDEX
    Explanations

    up and running

    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
     footing
    -0.10
    pios
    -0.10
    etc
    -0.09
    PIO
    -0.09
     Nich
    -0.09
    andler
    -0.09
     Sanford
    -0.08
    .qt
    -0.08
     spun
    -0.08
    /am
    -0.08
    POSITIVE LOGITS
     fis
    0.10
     ASAP
    0.09
    uml
    0.09
     Fus
    0.09
     McCl
    0.08
    åij¨æľŁ
    0.08
     sup
    0.08
    venge
    0.08
     fle
    0.08
     Lanc
    0.08
    Activations Density 0.170%

    No Known Activations