© 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. 17604
    Prev
    Next
    INDEX
    Explanations

    third Sunday

    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
     Neville
    -0.10
    alytics
    -0.10
     analytics
    -0.09
     Leia
    -0.09
     Finn
    -0.09
     MATLAB
    -0.09
     Kohana
    -0.09
     Chew
    -0.08
    idf
    -0.08
     Indy
    -0.08
    POSITIVE LOGITS
     Principal
    0.11
    DSL
    0.10
     Windsor
    0.10
     Coupons
    0.10
     divorce
    0.10
     transistor
    0.10
     neighbor
    0.10
     Drill
    0.10
     diaper
    0.10
     coupons
    0.10
    Activations Density 0.470%

    No Known Activations