© 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. 29325
    Prev
    Next
    INDEX
    Explanations

    is of or is wound

    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
     sui
    -0.08
    dbg
    -0.08
    edo
    -0.08
     goof
    -0.08
     spd
    -0.08
     bree
    -0.07
     compliments
    -0.07
     Guil
    -0.07
     vive
    -0.07
     mau
    -0.07
    POSITIVE LOGITS
    /is
    0.11
    nio
    0.11
     Kop
    0.11
     kop
    0.11
     elek
    0.10
     écrit
    0.10
    lsen
    0.10
    ACS
    0.10
    “But
    0.10
    mai
    0.09
    Activations Density 0.002%

    No Known Activations