© 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. 16313
    Prev
    Next
    INDEX
    Explanations

    encoding artifacts

    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
     Ore
    -0.09
     Veg
    -0.09
     otherwise
    -0.08
    CUR
    -0.08
     Cunning
    -0.08
    anno
    -0.08
     Temper
    -0.08
     weekends
    -0.08
     ser
    -0.08
     Zu
    -0.08
    POSITIVE LOGITS
     cheek
    0.11
     beaten
    0.11
    s
    0.10
    £
    0.10
     rever
    0.10
     forcing
    0.10
     tall
    0.09
    rez
    0.09
     obsess
    0.09
     banging
    0.09
    Activations Density 0.068%

    No Known Activations