© 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. 15571
    Prev
    Next
    INDEX
    Explanations

    right or wrong decision

    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
     humble
    -0.11
     improperly
    -0.10
     Sk
    -0.10
     gate
    -0.09
     nour
    -0.09
     uber
    -0.09
     unders
    -0.09
     humility
    -0.09
    hum
    -0.08
     entr
    -0.08
    POSITIVE LOGITS
     Manson
    0.10
    -inv
    0.10
     Hairst
    0.09
     Fuse
    0.08
    atas
    0.08
     intervened
    0.08
     Pes
    0.08
     sprinkle
    0.08
     Drill
    0.08
     PLL
    0.08
    Activations Density 0.002%

    No Known Activations