© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 7499
    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
     nud
    -0.11
    hausen
    -0.11
     cuk
    -0.10
     kö
    -0.10
     Dorm
    -0.10
     Mehr
    -0.10
    adesh
    -0.10
     lem
    -0.10
    bourg
    -0.10
    imd
    -0.10
    POSITIVE LOGITS
    ulo
    0.11
     Amb
    0.09
     Hass
    0.08
    844
    0.08
     hitch
    0.08
    iou
    0.08
    arel
    0.08
     crave
    0.08
    ampa
    0.07
     Depart
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.