© 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. 30026
    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
    wig
    -0.08
    ivi
    -0.08
    utow
    -0.08
     rubber
    -0.07
     wax
    -0.07
     joked
    -0.07
    -hole
    -0.07
     improvis
    -0.07
     Weinstein
    -0.07
     consciously
    -0.07
    POSITIVE LOGITS
     drove
    0.13
     driving
    0.12
     arrive
    0.12
     Drive
    0.12
     drive
    0.12
     downstairs
    0.11
     arrives
    0.11
     Phonetic
    0.11
     drives
    0.11
     transporting
    0.11
    Activations Density 0.000%

    No Known Activations