© 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. 29069
    Prev
    Next
    INDEX
    Explanations

    revealing or showing something

    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
    onet
    -0.10
    OBJ
    -0.09
    /ac
    -0.09
    pivot
    -0.09
     upro
    -0.09
    (SP
    -0.09
     inv
    -0.08
    .blur
    -0.08
     parc
    -0.08
     Main
    -0.08
    POSITIVE LOGITS
     exposed
    0.35
     visible
    0.32
     uncovered
    0.30
     peek
    0.27
     Visible
    0.26
    Exposed
    0.25
     glimps
    0.23
    visible
    0.23
    -visible
    0.23
    Visible
    0.22
    Activations Density 0.313%

    No Known Activations