© 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. 88771
    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
    -du
    -0.09
    receipt
    -0.09
     prolific
    -0.09
    elling
    -0.09
    /pre
    -0.09
    rei
    -0.09
     nei
    -0.09
    mie
    -0.09
    -pos
    -0.09
     Simpson
    -0.09
    POSITIVE LOGITS
     pairs
    0.11
     siblings
    0.11
    alu
    0.10
     Husband
    0.10
    Pairs
    0.10
    Ø°
    0.10
     accommodating
    0.10
     Couples
    0.10
    _pairs
    0.10
     couples
    0.09
    Activations Density 0.000%

    No Known Activations