© 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. 47212
    Prev
    Next
    INDEX
    Explanations

    first, largest, only, whole

    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
    hardt
    -0.09
    Both
    -0.09
    both
    -0.09
     BOTH
    -0.09
     both
    -0.09
     Both
    -0.08
     Operand
    -0.08
    owski
    -0.08
     Chattanooga
    -0.08
    AccountId
    -0.08
    POSITIVE LOGITS
     youngest
    0.26
     largest
    0.26
     first
    0.25
     oldest
    0.25
     longest
    0.24
     fourth
    0.24
     eldest
    0.22
     tallest
    0.22
     newest
    0.22
     last
    0.22
    Activations Density 0.918%

    No Known Activations