© 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. 31075
    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
     tox
    -0.11
     Savannah
    -0.11
    ideos
    -0.10
     zam
    -0.10
     kun
    -0.09
    abez
    -0.09
     Kun
    -0.09
    orte
    -0.09
    Dat
    -0.09
     Bip
    -0.09
    POSITIVE LOGITS
     Larson
    0.09
    rd
    0.08
     attached
    0.08
     delight
    0.07
     renew
    0.07
    apon
    0.07
     Mong
    0.07
     Kirst
    0.07
     Lange
    0.07
     tear
    0.07
    Activations Density 0.000%

    No Known Activations