© 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. 92045
    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
     Mund
    -0.08
     XSS
    -0.08
    éri
    -0.08
    underline
    -0.07
     Erect
    -0.07
    phant
    -0.07
     hikes
    -0.07
     destiny
    -0.07
     Dustin
    -0.07
     literal
    -0.07
    POSITIVE LOGITS
     present
    0.10
    IFn
    0.10
    rzy
    0.10
     Rings
    0.10
     Bat
    0.10
    nings
    0.10
    etter
    0.10
    aga
    0.10
    dq
    0.09
     dat
    0.09
    Activations Density 0.000%

    No Known Activations