© 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. 49881
    Prev
    Next
    INDEX
    Explanations

    relaxation, license, behavioral

    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
     bare
    -0.10
     Bart
    -0.09
    cka
    -0.08
     gre
    -0.08
    bard
    -0.08
     Huck
    -0.08
     Boeh
    -0.08
    ogn
    -0.08
    .wh
    -0.07
     Sutton
    -0.07
    POSITIVE LOGITS
     Punch
    0.11
     floppy
    0.11
     stumbling
    0.10
     Maur
    0.10
     reversible
    0.10
    /pop
    0.10
     Maar
    0.10
     Lem
    0.10
    **/↵↵
    0.10
     Pas
    0.09
    Activations Density 0.005%

    No Known Activations