© 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. 29982
    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
     everyone
    -0.10
     vulnerability
    -0.09
    inite
    -0.09
     multif
    -0.09
    LOGGER
    -0.08
     layered
    -0.08
     Heck
    -0.08
    init
    -0.08
     Joel
    -0.08
     cho
    -0.08
    POSITIVE LOGITS
     zwar
    0.11
    leur
    0.10
     intim
    0.10
     Regents
    0.10
    indow
    0.10
     Scrolls
    0.10
    wu
    0.10
    pressure
    0.10
     dumps
    0.10
    prs
    0.10
    Activations Density 0.000%

    No Known Activations