© 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. 26115
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    icha
    -0.10
     zer
    -0.09
     Prism
    -0.09
    iggs
    -0.09
    inator
    -0.09
    dzi
    -0.08
     leveling
    -0.08
     Gale
    -0.08
    HAL
    -0.08
    ippi
    -0.08
    POSITIVE LOGITS
     no
    0.18
     doubt
    0.16
     longer
    0.13
     matter
    0.13
     reason
    0.12
    things
    0.12
     trace
    0.12
     mercy
    0.11
     qual
    0.11
     traces
    0.11
    Activations Density 0.000%

    No Known Activations