© 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. 30545
    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
    fte
    -0.09
     Saints
    -0.09
    anks
    -0.09
     inf
    -0.09
     ordered
    -0.09
     Glow
    -0.09
    ité
    -0.09
     sockets
    -0.08
     because
    -0.08
     errno
    -0.08
    POSITIVE LOGITS
     membership
    0.11
     Membership
    0.10
     Either
    0.09
    rial
    0.09
     either
    0.09
     Scout
    0.09
    asper
    0.09
    -basic
    0.08
    coma
    0.08
    atch
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.