© 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. 116429
    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
    avin
    -0.09
    agos
    -0.09
     cherry
    -0.08
    antar
    -0.08
     acces
    -0.08
     Crawford
    -0.08
     luc
    -0.08
    istan
    -0.08
     chill
    -0.08
     Fancy
    -0.08
    POSITIVE LOGITS
    abet
    0.12
     Gard
    0.10
     taxing
    0.10
    PF
    0.10
     Plant
    0.09
     meno
    0.09
    Kn
    0.09
     mrb
    0.09
    bio
    0.09
     Stout
    0.09
    Activations Density 0.000%

    No Known Activations