© 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. 116718
    Prev
    Next
    INDEX
    Explanations

    VA, HA, GA, WA, TA initialisms

    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
    mania
    -0.10
    atti
    -0.10
    ardo
    -0.09
    ardy
    -0.09
    ij
    -0.09
    erver
    -0.09
    ë¡Ŀ
    -0.09
    lagen
    -0.09
    tat
    -0.08
    gram
    -0.08
    POSITIVE LOGITS
    quet
    0.11
    unted
    0.11
    resses
    0.11
    ught
    0.11
    untlet
    0.11
    resh
    0.10
    ressing
    0.10
    åŁ
    0.10
    yers
    0.10
    iley
    0.10
    Activations Density 0.161%

    No Known Activations