© 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. 5215
    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
    ofi
    -0.09
     rue
    -0.09
     ledger
    -0.09
    anche
    -0.09
    ledger
    -0.08
     Ago
    -0.08
    avl
    -0.08
     sodom
    -0.08
    adem
    -0.08
     Scrolls
    -0.08
    POSITIVE LOGITS
    uku
    0.10
    374
    0.10
     trad
    0.10
     wa
    0.09
     replic
    0.09
     linger
    0.09
     standby
    0.09
     cath
    0.09
    æ³
    0.09
     pa
    0.09
    Activations Density 0.000%

    No Known Activations