© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7968
    Prev
    Next
    INDEX
    Explanations

    legal citations with years

    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
     Dere
    -0.13
    -SA
    -0.10
     PTR
    -0.10
    isser
    -0.10
    ĵį
    -0.10
     ages
    -0.09
     Strait
    -0.09
    -loader
    -0.09
     dere
    -0.09
     textured
    -0.09
    POSITIVE LOGITS
     Rudy
    0.08
     trump
    0.08
    /form
    0.08
     Soda
    0.07
     pies
    0.07
     Cot
    0.07
     Cand
    0.07
    otas
    0.07
     rut
    0.07
     chmod
    0.07
    Activations Density 0.284%

    No Known Activations