© 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. 29208
    Prev
    Next
    INDEX
    Explanations

    macro prefix

    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
     positives
    -0.11
    enticator
    -0.10
    -loader
    -0.10
     surviving
    -0.10
     Forbes
    -0.10
    æĿ¡
    -0.10
    agog
    -0.10
     bulls
    -0.10
     GOOGLE
    -0.10
    ori
    -0.09
    POSITIVE LOGITS
    bung
    0.09
     Ting
    0.09
     sok
    0.08
     Ney
    0.08
     uncon
    0.08
     intellect
    0.08
    alfa
    0.08
     Couple
    0.08
    bd
    0.07
    ars
    0.07
    Activations Density 0.014%

    No Known Activations