© 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. 50504
    Prev
    Next
    INDEX
    Explanations

    physical dimensions

    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
    Prompt
    -0.11
    -era
    -0.11
    ott
    -0.11
    -style
    -0.11
     Dou
    -0.11
     Crawford
    -0.11
    getti
    -0.11
     caval
    -0.10
     Viewer
    -0.10
    FU
    -0.10
    POSITIVE LOGITS
    /type
    0.10
    /configuration
    0.10
    -wise
    0.09
    /name
    0.09
    /style
    0.09
    /color
    0.08
    wise
    0.08
    lessness
    0.08
    /value
    0.08
     Ec
    0.08
    Activations Density 0.063%

    No Known Activations