© 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. 7690
    Prev
    Next
    INDEX
    Explanations

    wordplay and figurative language

    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
     Gri
    -0.10
    aton
    -0.09
     homogeneous
    -0.09
     WHY
    -0.09
     IO
    -0.08
    arton
    -0.08
    aly
    -0.08
     complain
    -0.08
     Bir
    -0.08
     Tib
    -0.08
    POSITIVE LOGITS
     unintended
    0.24
     intentional
    0.23
     unintention
    0.22
     deliberate
    0.18
     intentionally
    0.16
     pun
    0.16
     intended
    0.15
     inadvert
    0.15
     deliberately
    0.14
    pun
    0.14
    Activations Density 0.038%

    No Known Activations