© 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. 112160
    Prev
    Next
    INDEX
    Explanations

    action followed by more/comparative

    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
     nei
    -0.11
    iek
    -0.10
     mystery
    -0.10
    prime
    -0.10
     cater
    -0.09
     Already
    -0.09
    ativo
    -0.09
    	Use
    -0.09
    527
    -0.09
     prime
    -0.09
    POSITIVE LOGITS
     broader
    0.15
     elsewhere
    0.15
     harder
    0.14
     wider
    0.14
     higher
    0.14
     bigger
    0.14
     again
    0.13
     anymore
    0.13
     larger
    0.13
     more
    0.13
    Activations Density 0.141%

    No Known Activations