© 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. 115083
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ulu
    -0.09
    alert
    -0.09
    elt
    -0.09
     lo
    -0.08
     another
    -0.08
     dirt
    -0.08
    vel
    -0.08
     Bauer
    -0.08
    vl
    -0.08
    greg
    -0.08
    POSITIVE LOGITS
     exactly
    0.12
     approximately
    0.11
    akter
    0.10
     circa
    0.10
     precisely
    0.10
    actually
    0.10
     actu
    0.10
     dues
    0.10
     aprox
    0.10
     rehabilit
    0.10
    Activations Density 0.821%

    No Known Activations