© 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. 49577
    Prev
    Next
    INDEX
    Explanations

    Purkinje, protected, appealing, timed, paraganglioma

    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
    agua
    -0.09
    aho
    -0.08
    lds
    -0.08
    353
    -0.08
    HEY
    -0.08
     owed
    -0.08
     wan
    -0.08
     Panama
    -0.08
     Fresno
    -0.08
    ITO
    -0.08
    POSITIVE LOGITS
    âĢº
    0.09
     catalog
    0.08
     hood
    0.08
    aina
    0.08
     Vers
    0.08
     vers
    0.08
    č↵↵
    0.08
    -vers
    0.08
     indeed
    0.08
    utt
    0.08
    Activations Density 0.279%

    No Known Activations