© 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. 17182
    Prev
    Next
    INDEX
    Explanations

    maybe you can

    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
     ambit
    -0.09
    orna
    -0.07
    ood
    -0.07
     bit
    -0.07
     convention
    -0.07
     Gaines
    -0.07
     MAKE
    -0.07
     gn
    -0.07
    yl
    -0.07
     passe
    -0.07
    POSITIVE LOGITS
    ulle
    0.12
     Kel
    0.12
     misunderstood
    0.11
    ULD
    0.11
    isco
    0.11
     should
    0.10
    <?↵
    0.10
     Should
    0.10
     clar
    0.10
     lest
    0.10
    Activations Density 0.014%

    No Known Activations