© 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. 89462
    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
    uchar
    -0.10
    cls
    -0.09
     clap
    -0.09
    fish
    -0.09
    probe
    -0.09
    tpl
    -0.09
     babes
    -0.09
     discre
    -0.09
     Shapiro
    -0.09
    bes
    -0.09
    POSITIVE LOGITS
     mounting
    0.10
     headaches
    0.10
     rigid
    0.10
     pain
    0.10
     headache
    0.09
     pains
    0.09
     chron
    0.09
     my
    0.09
     Pain
    0.09
    neck
    0.08
    Activations Density 0.000%

    No Known Activations