© 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. 49003
    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
    ivable
    -0.09
     Lawson
    -0.08
    ki
    -0.08
     habitual
    -0.08
     Barry
    -0.08
    igua
    -0.08
     arising
    -0.08
     Sham
    -0.08
     newcomers
    -0.08
     embarrass
    -0.08
    POSITIVE LOGITS
    -IN
    0.10
     Cob
    0.10
    ater
    0.10
     caut
    0.09
     uplift
    0.09
    OUCH
    0.09
    inas
    0.09
     Kar
    0.09
    akit
    0.09
    agra
    0.09
    Activations Density 0.000%

    No Known Activations