© 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. 27084
    Prev
    Next
    INDEX
    Explanations

    where to find

    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
     sweep
    -0.13
    haps
    -0.11
     Sweep
    -0.11
    ___↵↵
    -0.10
     stimulus
    -0.10
    irez
    -0.10
    -animate
    -0.10
     atlas
    -0.10
     exercise
    -0.10
    presso
    -0.10
    POSITIVE LOGITS
    owa
    0.09
    leta
    0.08
     acquiring
    0.08
     rar
    0.08
     Can
    0.08
     derog
    0.08
    fore
    0.08
     do
    0.07
    ande
    0.07
     Elder
    0.07
    Activations Density 0.002%

    No Known Activations