© 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. 90831
    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
     Tent
    -0.10
    neh
    -0.10
    /open
    -0.08
    ottage
    -0.08
    orig
    -0.08
    /rest
    -0.08
     Glide
    -0.08
     Equ
    -0.08
    velt
    -0.08
     Differential
    -0.08
    POSITIVE LOGITS
    ettel
    0.10
     Jing
    0.10
     trif
    0.09
     caution
    0.09
    erring
    0.09
     Yoshi
    0.09
    TW
    0.09
    inton
    0.09
     intervening
    0.09
    qus
    0.09
    Activations Density 0.000%

    No Known Activations