© 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. 15691
    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
    -mult
    -0.11
     bil
    -0.10
     Vend
    -0.09
    erman
    -0.09
     comb
    -0.09
     targ
    -0.09
     ones
    -0.09
    rack
    -0.09
     Michaels
    -0.09
     Atl
    -0.08
    POSITIVE LOGITS
    izar
    0.10
    898
    0.10
    ierte
    0.10
    hear
    0.09
    emu
    0.09
    ju
    0.09
    aine
    0.09
     laps
    0.09
     advising
    0.09
    etus
    0.09
    Activations Density 0.000%

    No Known Activations