© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6162
    Prev
    Next
    INDEX
    Explanations

    preparation and calculation

    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
    ncia
    -0.10
    asper
    -0.10
     Vas
    -0.09
     Mans
    -0.09
     Fut
    -0.09
    inherit
    -0.09
     Tomorrow
    -0.08
     #%
    -0.08
     brit
    -0.08
    yne
    -0.08
    POSITIVE LOGITS
     cott
    0.09
     euch
    0.09
     undertaking
    0.09
     eer
    0.09
     arm
    0.08
     rect
    0.08
     Arm
    0.08
     Poll
    0.08
    ropp
    0.08
    yen
    0.08
    Activations Density 0.001%

    No Known Activations