© 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. 31371
    Prev
    Next
    INDEX
    Explanations

    dedicated to

    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
    /opt
    -0.13
    ANTE
    -0.12
    /animate
    -0.10
     Crane
    -0.10
     Dy
    -0.09
    apo
    -0.09
    .shtml
    -0.09
     Incre
    -0.09
    /avatar
    -0.09
     spectacle
    -0.09
    POSITIVE LOGITS
     dedicated
    0.11
     Dedicated
    0.10
     dedicate
    0.10
     Royals
    0.09
     Pall
    0.09
    ä¸ĵ
    0.08
     devoted
    0.08
     seper
    0.08
     blurred
    0.08
     Caj
    0.08
    Activations Density 0.001%

    No Known Activations