© 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. 47319
    Prev
    Next
    INDEX
    Explanations

    RSS feed

    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
    leigh
    -0.08
     dm
    -0.08
     surg
    -0.08
     FIR
    -0.08
    /options
    -0.07
    unday
    -0.07
     cose
    -0.07
    Interface
    -0.07
     scars
    -0.07
    lemen
    -0.07
    POSITIVE LOGITS
     mediated
    0.10
     gibi
    0.10
    (es
    0.10
    ROC
    0.09
     Crane
    0.09
    -mediated
    0.09
     scram
    0.09
     sponsorship
    0.09
     persistence
    0.09
     Pound
    0.09
    Activations Density 0.010%

    No Known Activations