© 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. 50004
    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
     Thorn
    -0.08
     nues
    -0.08
     satisf
    -0.08
     indem
    -0.08
    erton
    -0.08
     SHOW
    -0.08
    ettes
    -0.08
    Sink
    -0.08
    @SuppressWarnings
    -0.08
     ??
    -0.08
    POSITIVE LOGITS
     decided
    0.13
     decides
    0.13
     decide
    0.13
    ivet
    0.11
     immediately
    0.11
     XS
    0.10
     determined
    0.10
    erb
    0.10
     Decide
    0.10
    uter
    0.10
    Activations Density 0.000%

    No Known Activations