© 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. 27657
    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
     decre
    -0.08
     digest
    -0.08
     %.
    -0.07
    bone
    -0.07
     digestion
    -0.06
    Äĥr
    -0.06
    diag
    -0.06
    matic
    -0.06
     Digest
    -0.06
     Shore
    -0.06
    POSITIVE LOGITS
    ilm
    0.13
     Cres
    0.12
    ovel
    0.12
     Bij
    0.12
     Cath
    0.11
     cheat
    0.11
     authors
    0.11
     Williamson
    0.11
    evin
    0.11
     Princeton
    0.11
    Activations Density 0.000%

    No Known Activations