© 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. 50532
    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
     Horny
    -0.09
     Commissioners
    -0.09
    villa
    -0.09
    mue
    -0.08
    orny
    -0.08
     Sle
    -0.08
     Amer
    -0.08
     Civ
    -0.08
    edium
    -0.08
    imestep
    -0.08
    POSITIVE LOGITS
     fab
    0.11
    wt
    0.10
    dt
    0.09
     CHE
    0.09
    idot
    0.09
    otec
    0.09
     obey
    0.09
    .Framework
    0.09
    ombre
    0.09
     Fab
    0.09
    Activations Density 0.000%

    No Known Activations