© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16766
    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
    nost
    -0.10
     Sands
    -0.10
    opo
    -0.10
     dbname
    -0.09
     Vu
    -0.09
    awk
    -0.09
    alog
    -0.09
    /{}/
    -0.09
    "|
    -0.09
    alers
    -0.09
    POSITIVE LOGITS
     Nin
    0.11
    HQ
    0.09
     invariably
    0.08
     Tib
    0.08
     ARG
    0.08
     verdict
    0.08
    ulet
    0.08
    RAL
    0.08
    601
    0.08
    90
    0.07
    Activations Density 0.000%

    No Known Activations