© 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. 30480
    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
    份
    -0.07
    ecer
    -0.07
     swo
    -0.07
     coveted
    -0.07
     trophy
    -0.07
    iec
    -0.07
     Rol
    -0.07
     mö
    -0.07
     raft
    -0.07
     rebut
    -0.07
    POSITIVE LOGITS
    alah
    0.12
     inc
    0.12
     Chun
    0.11
     mechanically
    0.11
    /ajax
    0.11
     Patron
    0.11
     Plus
    0.11
     Buck
    0.11
    ?[
    0.11
    -Key
    0.11
    Activations Density 0.000%

    No Known Activations