© 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. 30529
    Prev
    Next
    INDEX
    Explanations

    achieve results quickly or permanently

    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
    WT
    -0.09
     Shuttle
    -0.08
     louder
    -0.08
     occasionally
    -0.08
     Snow
    -0.08
    alian
    -0.08
    erd
    -0.08
     loudly
    -0.08
     takeover
    -0.08
     Rage
    -0.08
    POSITIVE LOGITS
     overnight
    0.22
     quickly
    0.21
     permanently
    0.19
     inexp
    0.19
     Overnight
    0.18
     rapidly
    0.18
     Quickly
    0.17
     naturally
    0.17
     without
    0.16
     effortlessly
    0.16
    Activations Density 0.426%

    No Known Activations