© 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. 91768
    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
     spit
    -0.11
     Patricia
    -0.10
     (()
    -0.09
     schl
    -0.09
     Mat
    -0.09
     Cab
    -0.09
    OME
    -0.09
     Cut
    -0.09
     spat
    -0.09
     Samp
    -0.09
    POSITIVE LOGITS
    Anywhere
    0.09
    æĸĻ
    0.09
     central
    0.09
    getti
    0.08
    chet
    0.08
    Thor
    0.08
     Swimming
    0.08
    itta
    0.08
    eso
    0.08
     privileged
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.