© 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. 49062
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
     operation
    -0.10
     Cobb
    -0.10
     Sinclair
    -0.10
     closing
    -0.10
    Closing
    -0.10
     empty
    -0.10
     reopen
    -0.10
    745
    -0.10
     intimidation
    -0.09
    pii
    -0.09
    POSITIVE LOGITS
     door
    0.11
     doors
    0.09
    door
    0.09
     intervening
    0.09
    shal
    0.08
     bol
    0.08
     umbrella
    0.08
    fcn
    0.08
     bolt
    0.08
    rend
    0.08
    Activations Density 0.006%

    No Known Activations