© 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. 47091
    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
     States
    -0.09
    sonian
    -0.09
     Carm
    -0.09
     Govern
    -0.08
    -bot
    -0.08
     Berkeley
    -0.08
     Django
    -0.08
     Chop
    -0.08
    ingroup
    -0.08
    ụ
    -0.08
    POSITIVE LOGITS
    fur
    0.09
    fu
    0.09
    tion
    0.08
    inus
    0.08
    inh
    0.08
     fur
    0.08
    leta
    0.08
    .hu
    0.08
    orus
    0.08
    aten
    0.08
    Activations Density 0.000%

    No Known Activations