© 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. 46939
    Prev
    Next
    INDEX
    Explanations

    yielding or conceding

    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
     Downs
    -0.12
     unm
    -0.12
     Independ
    -0.11
     bounce
    -0.11
     lightly
    -0.10
    arlo
    -0.10
    -bars
    -0.10
     truncated
    -0.10
    tha
    -0.10
     rebound
    -0.10
    POSITIVE LOGITS
     gracefully
    0.12
     pressure
    0.11
     grac
    0.11
     prey
    0.09
     inevitable
    0.09
    ante
    0.09
    otos
    0.09
     pressures
    0.09
    ugs
    0.09
     superiority
    0.09
    Activations Density 0.025%

    No Known Activations