© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114871
    Prev
    Next
    INDEX
    Explanations

    want to or afford to

    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
     Ach
    -0.10
     Patterns
    -0.09
    436
    -0.09
     promot
    -0.09
     preference
    -0.09
    ogn
    -0.09
     fit
    -0.08
     reluctantly
    -0.08
    fy
    -0.08
     tal
    -0.08
    POSITIVE LOGITS
     complication
    0.17
     complications
    0.15
     added
    0.15
     additional
    0.13
     complic
    0.13
    adds
    0.13
     stress
    0.12
     distractions
    0.12
    added
    0.12
     Added
    0.11
    Activations Density 0.005%

    No Known Activations