© 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. 47370
    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
     Hess
    -0.09
     hus
    -0.09
    æ
    -0.09
     Ged
    -0.08
    asher
    -0.07
     Hull
    -0.07
    ibus
    -0.07
     generously
    -0.07
    inh
    -0.07
    RFC
    -0.07
    POSITIVE LOGITS
     Schw
    0.12
     Gul
    0.12
    —that
    0.10
     Incre
    0.10
     missed
    0.10
    arth
    0.10
    lemn
    0.10
     rep
    0.10
     Transitional
    0.10
    omal
    0.10
    Activations Density 0.000%

    No Known Activations